explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 10:16:27 +03:00
Code Issues Packages Projects Releases Wiki Activity
a62c38e1ef
spaCy/spacy/en.cpp

5964 lines
228 KiB
C++
Raw Normal View History

* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* Generated by Cython 0.20.1 on Mon Jul 7 01:14:44 2014 */
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
#define PY_SSIZE_T_CLEAN
#ifndef CYTHON_USE_PYLONG_INTERNALS
#ifdef PYLONG_BITS_IN_DIGIT
#define CYTHON_USE_PYLONG_INTERNALS 0
#else
#include "pyconfig.h"
#ifdef PYLONG_BITS_IN_DIGIT
#define CYTHON_USE_PYLONG_INTERNALS 1
#else
#define CYTHON_USE_PYLONG_INTERNALS 0
#endif
#endif
#endif
#include "Python.h"
#ifndef Py_PYTHON_H
#error Python headers needed to compile C extensions, please install development version of Python.
#elif PY_VERSION_HEX < 0x02040000
#error Cython requires Python 2.4+.
#else
#define CYTHON_ABI "0_20_1"
#include <stddef.h> /* For offsetof */
#ifndef offsetof
#define offsetof(type, member) ( (size_t) & ((type*)0) -> member )
#endif
#if !defined(WIN32) && !defined(MS_WINDOWS)
#ifndef __stdcall
#define __stdcall
#endif
#ifndef __cdecl
#define __cdecl
#endif
#ifndef __fastcall
#define __fastcall
#endif
#endif
#ifndef DL_IMPORT
#define DL_IMPORT(t) t
#endif
#ifndef DL_EXPORT
#define DL_EXPORT(t) t
#endif
#ifndef PY_LONG_LONG
#define PY_LONG_LONG LONG_LONG
#endif
#ifndef Py_HUGE_VAL
#define Py_HUGE_VAL HUGE_VAL
#endif
#ifdef PYPY_VERSION
#define CYTHON_COMPILING_IN_PYPY 1
#define CYTHON_COMPILING_IN_CPYTHON 0
#else
#define CYTHON_COMPILING_IN_PYPY 0
#define CYTHON_COMPILING_IN_CPYTHON 1
#endif
#if CYTHON_COMPILING_IN_PYPY
#define Py_OptimizeFlag 0
#endif
#if PY_VERSION_HEX < 0x02050000
typedef int Py_ssize_t;
#define PY_SSIZE_T_MAX INT_MAX
#define PY_SSIZE_T_MIN INT_MIN
#define PY_FORMAT_SIZE_T ""
#define CYTHON_FORMAT_SSIZE_T ""
#define PyInt_FromSsize_t(z) PyInt_FromLong(z)
#define PyInt_AsSsize_t(o) __Pyx_PyInt_As_int(o)
#define PyNumber_Index(o) ((PyNumber_Check(o) && !PyFloat_Check(o)) ? PyNumber_Int(o) : \
(PyErr_Format(PyExc_TypeError, \
"expected index value, got %.200s", Py_TYPE(o)->tp_name), \
(PyObject*)0))
#define __Pyx_PyIndex_Check(o) (PyNumber_Check(o) && !PyFloat_Check(o) && \
!PyComplex_Check(o))
#define PyIndex_Check __Pyx_PyIndex_Check
#define PyErr_WarnEx(category, message, stacklevel) PyErr_Warn(category, message)
#define __PYX_BUILD_PY_SSIZE_T "i"
#else
#define __PYX_BUILD_PY_SSIZE_T "n"
#define CYTHON_FORMAT_SSIZE_T "z"
#define __Pyx_PyIndex_Check PyIndex_Check
#endif
#if PY_VERSION_HEX < 0x02060000
#define Py_REFCNT(ob) (((PyObject*)(ob))->ob_refcnt)
#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
#define Py_SIZE(ob) (((PyVarObject*)(ob))->ob_size)
#define PyVarObject_HEAD_INIT(type, size) \
PyObject_HEAD_INIT(type) size,
#define PyType_Modified(t)
typedef struct {
void *buf;
PyObject *obj;
Py_ssize_t len;
Py_ssize_t itemsize;
int readonly;
int ndim;
char *format;
Py_ssize_t *shape;
Py_ssize_t *strides;
Py_ssize_t *suboffsets;
void *internal;
} Py_buffer;
#define PyBUF_SIMPLE 0
#define PyBUF_WRITABLE 0x0001
#define PyBUF_FORMAT 0x0004
#define PyBUF_ND 0x0008
#define PyBUF_STRIDES (0x0010 | PyBUF_ND)
#define PyBUF_C_CONTIGUOUS (0x0020 | PyBUF_STRIDES)
#define PyBUF_F_CONTIGUOUS (0x0040 | PyBUF_STRIDES)
#define PyBUF_ANY_CONTIGUOUS (0x0080 | PyBUF_STRIDES)
#define PyBUF_INDIRECT (0x0100 | PyBUF_STRIDES)
#define PyBUF_RECORDS (PyBUF_STRIDES | PyBUF_FORMAT | PyBUF_WRITABLE)
#define PyBUF_FULL (PyBUF_INDIRECT | PyBUF_FORMAT | PyBUF_WRITABLE)
typedef int (*getbufferproc)(PyObject *, Py_buffer *, int);
typedef void (*releasebufferproc)(PyObject *, Py_buffer *);
#endif
#if PY_MAJOR_VERSION < 3
#define __Pyx_BUILTIN_MODULE_NAME "__builtin__"
#define __Pyx_PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos) \
PyCode_New(a+k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)
#define __Pyx_DefaultClassType PyClass_Type
#else
#define __Pyx_BUILTIN_MODULE_NAME "builtins"
#define __Pyx_PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos) \
PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)
#define __Pyx_DefaultClassType PyType_Type
#endif
#if PY_VERSION_HEX < 0x02060000
#define PyUnicode_FromString(s) PyUnicode_Decode(s, strlen(s), "UTF-8", "strict")
#endif
#if PY_MAJOR_VERSION >= 3
#define Py_TPFLAGS_CHECKTYPES 0
#define Py_TPFLAGS_HAVE_INDEX 0
#endif
#if (PY_VERSION_HEX < 0x02060000) || (PY_MAJOR_VERSION >= 3)
#define Py_TPFLAGS_HAVE_NEWBUFFER 0
#endif
#if PY_VERSION_HEX < 0x02060000
#define Py_TPFLAGS_HAVE_VERSION_TAG 0
#endif
#if PY_VERSION_HEX < 0x02060000 && !defined(Py_TPFLAGS_IS_ABSTRACT)
#define Py_TPFLAGS_IS_ABSTRACT 0
#endif
#if PY_VERSION_HEX < 0x030400a1 && !defined(Py_TPFLAGS_HAVE_FINALIZE)
#define Py_TPFLAGS_HAVE_FINALIZE 0
#endif
#if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND)
#define CYTHON_PEP393_ENABLED 1
#define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ? \
0 : _PyUnicode_Ready((PyObject *)(op)))
#define __Pyx_PyUnicode_GET_LENGTH(u) PyUnicode_GET_LENGTH(u)
#define __Pyx_PyUnicode_READ_CHAR(u, i) PyUnicode_READ_CHAR(u, i)
#define __Pyx_PyUnicode_KIND(u) PyUnicode_KIND(u)
#define __Pyx_PyUnicode_DATA(u) PyUnicode_DATA(u)
#define __Pyx_PyUnicode_READ(k, d, i) PyUnicode_READ(k, d, i)
#else
#define CYTHON_PEP393_ENABLED 0
#define __Pyx_PyUnicode_READY(op) (0)
#define __Pyx_PyUnicode_GET_LENGTH(u) PyUnicode_GET_SIZE(u)
#define __Pyx_PyUnicode_READ_CHAR(u, i) ((Py_UCS4)(PyUnicode_AS_UNICODE(u)[i]))
#define __Pyx_PyUnicode_KIND(u) (sizeof(Py_UNICODE))
#define __Pyx_PyUnicode_DATA(u) ((void*)PyUnicode_AS_UNICODE(u))
#define __Pyx_PyUnicode_READ(k, d, i) ((void)(k), (Py_UCS4)(((Py_UNICODE*)d)[i]))
#endif
#if CYTHON_COMPILING_IN_PYPY
#define __Pyx_PyUnicode_Concat(a, b) PyNumber_Add(a, b)
#define __Pyx_PyUnicode_ConcatSafe(a, b) PyNumber_Add(a, b)
#else
#define __Pyx_PyUnicode_Concat(a, b) PyUnicode_Concat(a, b)
#define __Pyx_PyUnicode_ConcatSafe(a, b) ((unlikely((a) == Py_None) || unlikely((b) == Py_None)) ? \
PyNumber_Add(a, b) : __Pyx_PyUnicode_Concat(a, b))
#endif
#define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b))
#define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b))
#if PY_MAJOR_VERSION >= 3
#define __Pyx_PyString_Format(a, b) PyUnicode_Format(a, b)
#else
#define __Pyx_PyString_Format(a, b) PyString_Format(a, b)
#endif
#if PY_MAJOR_VERSION >= 3
#define PyBaseString_Type PyUnicode_Type
#define PyStringObject PyUnicodeObject
#define PyString_Type PyUnicode_Type
#define PyString_Check PyUnicode_Check
#define PyString_CheckExact PyUnicode_CheckExact
#endif
#if PY_VERSION_HEX < 0x02060000
#define PyBytesObject PyStringObject
#define PyBytes_Type PyString_Type
#define PyBytes_Check PyString_Check
#define PyBytes_CheckExact PyString_CheckExact
#define PyBytes_FromString PyString_FromString
#define PyBytes_FromStringAndSize PyString_FromStringAndSize
#define PyBytes_FromFormat PyString_FromFormat
#define PyBytes_DecodeEscape PyString_DecodeEscape
#define PyBytes_AsString PyString_AsString
#define PyBytes_AsStringAndSize PyString_AsStringAndSize
#define PyBytes_Size PyString_Size
#define PyBytes_AS_STRING PyString_AS_STRING
#define PyBytes_GET_SIZE PyString_GET_SIZE
#define PyBytes_Repr PyString_Repr
#define PyBytes_Concat PyString_Concat
#define PyBytes_ConcatAndDel PyString_ConcatAndDel
#endif
#if PY_MAJOR_VERSION >= 3
#define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj)
#define __Pyx_PyBaseString_CheckExact(obj) PyUnicode_CheckExact(obj)
#else
#define __Pyx_PyBaseString_Check(obj) (PyString_CheckExact(obj) || PyUnicode_CheckExact(obj) || \
PyString_Check(obj) || PyUnicode_Check(obj))
#define __Pyx_PyBaseString_CheckExact(obj) (PyString_CheckExact(obj) || PyUnicode_CheckExact(obj))
#endif
#if PY_VERSION_HEX < 0x02060000
#define PySet_Check(obj) PyObject_TypeCheck(obj, &PySet_Type)
#define PyFrozenSet_Check(obj) PyObject_TypeCheck(obj, &PyFrozenSet_Type)
#endif
#ifndef PySet_CheckExact
#define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type)
#endif
#define __Pyx_TypeCheck(obj, type) PyObject_TypeCheck(obj, (PyTypeObject *)type)
#if PY_MAJOR_VERSION >= 3
#define PyIntObject PyLongObject
#define PyInt_Type PyLong_Type
#define PyInt_Check(op) PyLong_Check(op)
#define PyInt_CheckExact(op) PyLong_CheckExact(op)
#define PyInt_FromString PyLong_FromString
#define PyInt_FromUnicode PyLong_FromUnicode
#define PyInt_FromLong PyLong_FromLong
#define PyInt_FromSize_t PyLong_FromSize_t
#define PyInt_FromSsize_t PyLong_FromSsize_t
#define PyInt_AsLong PyLong_AsLong
#define PyInt_AS_LONG PyLong_AS_LONG
#define PyInt_AsSsize_t PyLong_AsSsize_t
#define PyInt_AsUnsignedLongMask PyLong_AsUnsignedLongMask
#define PyInt_AsUnsignedLongLongMask PyLong_AsUnsignedLongLongMask
#define PyNumber_Int PyNumber_Long
#endif
#if PY_MAJOR_VERSION >= 3
#define PyBoolObject PyLongObject
#endif
#if PY_VERSION_HEX < 0x030200A4
typedef long Py_hash_t;
#define __Pyx_PyInt_FromHash_t PyInt_FromLong
#define __Pyx_PyInt_AsHash_t PyInt_AsLong
#else
#define __Pyx_PyInt_FromHash_t PyInt_FromSsize_t
#define __Pyx_PyInt_AsHash_t PyInt_AsSsize_t
#endif
#if (PY_MAJOR_VERSION < 3) || (PY_VERSION_HEX >= 0x03010300)
#define __Pyx_PySequence_GetSlice(obj, a, b) PySequence_GetSlice(obj, a, b)
#define __Pyx_PySequence_SetSlice(obj, a, b, value) PySequence_SetSlice(obj, a, b, value)
#define __Pyx_PySequence_DelSlice(obj, a, b) PySequence_DelSlice(obj, a, b)
#else
#define __Pyx_PySequence_GetSlice(obj, a, b) (unlikely(!(obj)) ? \
(PyErr_SetString(PyExc_SystemError, "null argument to internal routine"), (PyObject*)0) : \
(likely((obj)->ob_type->tp_as_mapping) ? (PySequence_GetSlice(obj, a, b)) : \
(PyErr_Format(PyExc_TypeError, "'%.200s' object is unsliceable", (obj)->ob_type->tp_name), (PyObject*)0)))
#define __Pyx_PySequence_SetSlice(obj, a, b, value) (unlikely(!(obj)) ? \
(PyErr_SetString(PyExc_SystemError, "null argument to internal routine"), -1) : \
(likely((obj)->ob_type->tp_as_mapping) ? (PySequence_SetSlice(obj, a, b, value)) : \
(PyErr_Format(PyExc_TypeError, "'%.200s' object doesn't support slice assignment", (obj)->ob_type->tp_name), -1)))
#define __Pyx_PySequence_DelSlice(obj, a, b) (unlikely(!(obj)) ? \
(PyErr_SetString(PyExc_SystemError, "null argument to internal routine"), -1) : \
(likely((obj)->ob_type->tp_as_mapping) ? (PySequence_DelSlice(obj, a, b)) : \
(PyErr_Format(PyExc_TypeError, "'%.200s' object doesn't support slice deletion", (obj)->ob_type->tp_name), -1)))
#endif
#if PY_MAJOR_VERSION >= 3
#define PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func))
#endif
#if PY_VERSION_HEX < 0x02050000
#define __Pyx_GetAttrString(o,n) PyObject_GetAttrString((o),((char *)(n)))
#define __Pyx_SetAttrString(o,n,a) PyObject_SetAttrString((o),((char *)(n)),(a))
#define __Pyx_DelAttrString(o,n) PyObject_DelAttrString((o),((char *)(n)))
#else
#define __Pyx_GetAttrString(o,n) PyObject_GetAttrString((o),(n))
#define __Pyx_SetAttrString(o,n,a) PyObject_SetAttrString((o),(n),(a))
#define __Pyx_DelAttrString(o,n) PyObject_DelAttrString((o),(n))
#endif
#if PY_VERSION_HEX < 0x02050000
#define __Pyx_NAMESTR(n) ((char *)(n))
#define __Pyx_DOCSTR(n) ((char *)(n))
#else
#define __Pyx_NAMESTR(n) (n)
#define __Pyx_DOCSTR(n) (n)
#endif
#ifndef CYTHON_INLINE
#if defined(__GNUC__)
#define CYTHON_INLINE __inline__
#elif defined(_MSC_VER)
#define CYTHON_INLINE __inline
#elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
#define CYTHON_INLINE inline
#else
#define CYTHON_INLINE
#endif
#endif
#ifndef CYTHON_RESTRICT
#if defined(__GNUC__)
#define CYTHON_RESTRICT __restrict__
#elif defined(_MSC_VER) && _MSC_VER >= 1400
#define CYTHON_RESTRICT __restrict
#elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
#define CYTHON_RESTRICT restrict
#else
#define CYTHON_RESTRICT
#endif
#endif
#ifdef NAN
#define __PYX_NAN() ((float) NAN)
#else
static CYTHON_INLINE float __PYX_NAN() {
/* Initialize NaN. The sign is irrelevant, an exponent with all bits 1 and
a nonzero mantissa means NaN. If the first bit in the mantissa is 1, it is
a quiet NaN. */
float value;
memset(&value, 0xFF, sizeof(value));
return value;
}
#endif
#if PY_MAJOR_VERSION >= 3
#define __Pyx_PyNumber_Divide(x,y) PyNumber_TrueDivide(x,y)
#define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceTrueDivide(x,y)
#else
#define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y)
#define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y)
#endif
#ifndef __PYX_EXTERN_C
#ifdef __cplusplus
#define __PYX_EXTERN_C extern "C"
#else
#define __PYX_EXTERN_C extern
#endif
#endif
#if defined(WIN32) || defined(MS_WINDOWS)
#define _USE_MATH_DEFINES
#endif
#include <math.h>
#define __PYX_HAVE__spacy__en
#define __PYX_HAVE_API__spacy__en
#include <utility>
#include "ios"
#include "new"
#include "stdexcept"
#include "typeinfo"
#include <vector>
#include "stdint.h"
#include "sparsehash/dense_hash_map"
#include "string.h"
#include "stdlib.h"
#include "../include/MurmurHash3.h"
#include "../include/MurmurHash2.h"
#ifdef _OPENMP
#include <omp.h>
#endif /* _OPENMP */
#ifdef PYREX_WITHOUT_ASSERTIONS
#define CYTHON_WITHOUT_ASSERTIONS
#endif
#ifndef CYTHON_UNUSED
# if defined(__GNUC__)
# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4))
# define CYTHON_UNUSED __attribute__ ((__unused__))
# else
# define CYTHON_UNUSED
# endif
# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER))
# define CYTHON_UNUSED __attribute__ ((__unused__))
# else
# define CYTHON_UNUSED
# endif
#endif
typedef struct {PyObject **p; char *s; const Py_ssize_t n; const char* encoding;
const char is_unicode; const char is_str; const char intern; } __Pyx_StringTabEntry; /*proto*/
#define __PYX_DEFAULT_STRING_ENCODING_IS_ASCII 0
#define __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT 0
#define __PYX_DEFAULT_STRING_ENCODING ""
#define __Pyx_PyObject_FromString __Pyx_PyBytes_FromString
#define __Pyx_PyObject_FromStringAndSize __Pyx_PyBytes_FromStringAndSize
#define __Pyx_fits_Py_ssize_t(v, type, is_signed) ( \
(sizeof(type) < sizeof(Py_ssize_t)) || \
(sizeof(type) > sizeof(Py_ssize_t) && \
likely(v < (type)PY_SSIZE_T_MAX || \
v == (type)PY_SSIZE_T_MAX) && \
(!is_signed || likely(v > (type)PY_SSIZE_T_MIN || \
v == (type)PY_SSIZE_T_MIN))) || \
(sizeof(type) == sizeof(Py_ssize_t) && \
(is_signed || likely(v < (type)PY_SSIZE_T_MAX || \
v == (type)PY_SSIZE_T_MAX))) )
static CYTHON_INLINE char* __Pyx_PyObject_AsString(PyObject*);
static CYTHON_INLINE char* __Pyx_PyObject_AsStringAndSize(PyObject*, Py_ssize_t* length);
#define __Pyx_PyByteArray_FromString(s) PyByteArray_FromStringAndSize((const char*)s, strlen((const char*)s))
#define __Pyx_PyByteArray_FromStringAndSize(s, l) PyByteArray_FromStringAndSize((const char*)s, l)
#define __Pyx_PyBytes_FromString PyBytes_FromString
#define __Pyx_PyBytes_FromStringAndSize PyBytes_FromStringAndSize
static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(char*);
#if PY_MAJOR_VERSION < 3
#define __Pyx_PyStr_FromString __Pyx_PyBytes_FromString
#define __Pyx_PyStr_FromStringAndSize __Pyx_PyBytes_FromStringAndSize
#else
#define __Pyx_PyStr_FromString __Pyx_PyUnicode_FromString
#define __Pyx_PyStr_FromStringAndSize __Pyx_PyUnicode_FromStringAndSize
#endif
#define __Pyx_PyObject_AsSString(s) ((signed char*) __Pyx_PyObject_AsString(s))
#define __Pyx_PyObject_AsUString(s) ((unsigned char*) __Pyx_PyObject_AsString(s))
#define __Pyx_PyObject_FromUString(s) __Pyx_PyObject_FromString((char*)s)
#define __Pyx_PyBytes_FromUString(s) __Pyx_PyBytes_FromString((char*)s)
#define __Pyx_PyByteArray_FromUString(s) __Pyx_PyByteArray_FromString((char*)s)
#define __Pyx_PyStr_FromUString(s) __Pyx_PyStr_FromString((char*)s)
#define __Pyx_PyUnicode_FromUString(s) __Pyx_PyUnicode_FromString((char*)s)
#if PY_MAJOR_VERSION < 3
static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u)
{
const Py_UNICODE *u_end = u;
while (*u_end++) ;
return u_end - u - 1;
}
#else
#define __Pyx_Py_UNICODE_strlen Py_UNICODE_strlen
#endif
#define __Pyx_PyUnicode_FromUnicode(u) PyUnicode_FromUnicode(u, __Pyx_Py_UNICODE_strlen(u))
#define __Pyx_PyUnicode_FromUnicodeAndLength PyUnicode_FromUnicode
#define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode
#define __Pyx_Owned_Py_None(b) (Py_INCREF(Py_None), Py_None)
#define __Pyx_PyBool_FromLong(b) ((b) ? (Py_INCREF(Py_True), Py_True) : (Py_INCREF(Py_False), Py_False))
static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*);
static CYTHON_INLINE PyObject* __Pyx_PyNumber_Int(PyObject* x);
static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject*);
static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t);
#if CYTHON_COMPILING_IN_CPYTHON
#define __pyx_PyFloat_AsDouble(x) (PyFloat_CheckExact(x) ? PyFloat_AS_DOUBLE(x) : PyFloat_AsDouble(x))
#else
#define __pyx_PyFloat_AsDouble(x) PyFloat_AsDouble(x)
#endif
#define __pyx_PyFloat_AsFloat(x) ((float) __pyx_PyFloat_AsDouble(x))
#if PY_MAJOR_VERSION < 3 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
static int __Pyx_sys_getdefaultencoding_not_ascii;
static int __Pyx_init_sys_getdefaultencoding_params(void) {
PyObject* sys = NULL;
PyObject* default_encoding = NULL;
PyObject* ascii_chars_u = NULL;
PyObject* ascii_chars_b = NULL;
sys = PyImport_ImportModule("sys");
if (sys == NULL) goto bad;
default_encoding = PyObject_CallMethod(sys, (char*) (const char*) "getdefaultencoding", NULL);
if (default_encoding == NULL) goto bad;
if (strcmp(PyBytes_AsString(default_encoding), "ascii") == 0) {
__Pyx_sys_getdefaultencoding_not_ascii = 0;
} else {
const char* default_encoding_c = PyBytes_AS_STRING(default_encoding);
char ascii_chars[128];
int c;
for (c = 0; c < 128; c++) {
ascii_chars[c] = c;
}
__Pyx_sys_getdefaultencoding_not_ascii = 1;
ascii_chars_u = PyUnicode_DecodeASCII(ascii_chars, 128, NULL);
if (ascii_chars_u == NULL) goto bad;
ascii_chars_b = PyUnicode_AsEncodedString(ascii_chars_u, default_encoding_c, NULL);
if (ascii_chars_b == NULL || strncmp(ascii_chars, PyBytes_AS_STRING(ascii_chars_b), 128) != 0) {
PyErr_Format(
PyExc_ValueError,
"This module compiled with c_string_encoding=ascii, but default encoding '%.200s' is not a superset of ascii.",
default_encoding_c);
goto bad;
}
}
Py_XDECREF(sys);
Py_XDECREF(default_encoding);
Py_XDECREF(ascii_chars_u);
Py_XDECREF(ascii_chars_b);
return 0;
bad:
Py_XDECREF(sys);
Py_XDECREF(default_encoding);
Py_XDECREF(ascii_chars_u);
Py_XDECREF(ascii_chars_b);
return -1;
}
#endif
#if __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT && PY_MAJOR_VERSION >= 3
#define __Pyx_PyUnicode_FromStringAndSize(c_str, size) PyUnicode_DecodeUTF8(c_str, size, NULL)
#else
#define __Pyx_PyUnicode_FromStringAndSize(c_str, size) PyUnicode_Decode(c_str, size, __PYX_DEFAULT_STRING_ENCODING, NULL)
#if __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT
static char* __PYX_DEFAULT_STRING_ENCODING;
static int __Pyx_init_sys_getdefaultencoding_params(void) {
PyObject* sys = NULL;
PyObject* default_encoding = NULL;
char* default_encoding_c;
sys = PyImport_ImportModule("sys");
if (sys == NULL) goto bad;
default_encoding = PyObject_CallMethod(sys, (char*) (const char*) "getdefaultencoding", NULL);
if (default_encoding == NULL) goto bad;
default_encoding_c = PyBytes_AS_STRING(default_encoding);
__PYX_DEFAULT_STRING_ENCODING = (char*) malloc(strlen(default_encoding_c));
strcpy(__PYX_DEFAULT_STRING_ENCODING, default_encoding_c);
Py_DECREF(sys);
Py_DECREF(default_encoding);
return 0;
bad:
Py_XDECREF(sys);
Py_XDECREF(default_encoding);
return -1;
}
#endif
#endif
#ifdef __GNUC__
/* Test for GCC > 2.95 */
#if __GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95))
#define likely(x) __builtin_expect(!!(x), 1)
#define unlikely(x) __builtin_expect(!!(x), 0)
#else /* __GNUC__ > 2 ... */
#define likely(x) (x)
#define unlikely(x) (x)
#endif /* __GNUC__ > 2 ... */
#else /* __GNUC__ */
#define likely(x) (x)
#define unlikely(x) (x)
#endif /* __GNUC__ */
static PyObject *__pyx_m;
static PyObject *__pyx_d;
static PyObject *__pyx_b;
static PyObject *__pyx_empty_tuple;
static PyObject *__pyx_empty_bytes;
static int __pyx_lineno;
static int __pyx_clineno = 0;
static const char * __pyx_cfilenm= __FILE__;
static const char *__pyx_filename;
static const char *__pyx_f[] = {
"en.pyx",
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
"stringsource",
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
};
/* "spacy/lexeme.pxd":4
*
*
* ctypedef int ClusterID # <<<<<<<<<<<<<<
* ctypedef uint64_t StringHash
*
*/
typedef int __pyx_t_5spacy_6lexeme_ClusterID;
/* "spacy/lexeme.pxd":5
*
* ctypedef int ClusterID
* ctypedef uint64_t StringHash # <<<<<<<<<<<<<<
*
*
*/
typedef uint64_t __pyx_t_5spacy_6lexeme_StringHash;
/* "spacy/en.pxd":7
*
* ctypedef Py_UNICODE* string_ptr
* ctypedef size_t Lexeme_addr # For python interop # <<<<<<<<<<<<<<
* ctypedef Lexeme* Lexeme_ptr
*
*/
typedef size_t __pyx_t_5spacy_2en_Lexeme_addr;
/*--- Type declarations ---*/
struct __pyx_t_5spacy_6lexeme_Lexeme;
/* "spacy/lexeme.pxd":27
* # over the Lexeme, via:
* # for field in range(LexAttr.n): get_attr(Lexeme*, field)
* cdef enum HashFields: # <<<<<<<<<<<<<<
* sic
* lex
*/
enum __pyx_t_5spacy_6lexeme_HashFields {
__pyx_e_5spacy_6lexeme_sic,
__pyx_e_5spacy_6lexeme_lex,
__pyx_e_5spacy_6lexeme_normed,
__pyx_e_5spacy_6lexeme_cluster,
__pyx_e_5spacy_6lexeme_n
};
/* "spacy/lexeme.pxd":8
*
*
* cdef struct Lexeme: # <<<<<<<<<<<<<<
* StringHash sic # Hash of the original string
* StringHash lex # Hash of the word, with punctuation and clitics split off
*/
struct __pyx_t_5spacy_6lexeme_Lexeme {
__pyx_t_5spacy_6lexeme_StringHash sic;
__pyx_t_5spacy_6lexeme_StringHash lex;
__pyx_t_5spacy_6lexeme_StringHash normed;
__pyx_t_5spacy_6lexeme_StringHash last3;
Py_UNICODE first;
double prob;
__pyx_t_5spacy_6lexeme_ClusterID cluster;
int oft_upper;
int oft_title;
struct __pyx_t_5spacy_6lexeme_Lexeme *tail;
};
/* "spacy/en.pxd":6
*
*
* ctypedef Py_UNICODE* string_ptr # <<<<<<<<<<<<<<
* ctypedef size_t Lexeme_addr # For python interop
* ctypedef Lexeme* Lexeme_ptr
*/
typedef Py_UNICODE *__pyx_t_5spacy_2en_string_ptr;
/* "spacy/en.pxd":8
* ctypedef Py_UNICODE* string_ptr
* ctypedef size_t Lexeme_addr # For python interop
* ctypedef Lexeme* Lexeme_ptr # <<<<<<<<<<<<<<
*
*
*/
typedef struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_t_5spacy_2en_Lexeme_ptr;
#ifndef CYTHON_REFNANNY
#define CYTHON_REFNANNY 0
#endif
#if CYTHON_REFNANNY
typedef struct {
void (*INCREF)(void*, PyObject*, int);
void (*DECREF)(void*, PyObject*, int);
void (*GOTREF)(void*, PyObject*, int);
void (*GIVEREF)(void*, PyObject*, int);
void* (*SetupContext)(const char*, int, const char*);
void (*FinishContext)(void**);
} __Pyx_RefNannyAPIStruct;
static __Pyx_RefNannyAPIStruct *__Pyx_RefNanny = NULL;
static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname); /*proto*/
#define __Pyx_RefNannyDeclarations void *__pyx_refnanny = NULL;
#ifdef WITH_THREAD
#define __Pyx_RefNannySetupContext(name, acquire_gil) \
if (acquire_gil) { \
PyGILState_STATE __pyx_gilstate_save = PyGILState_Ensure(); \
__pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__); \
PyGILState_Release(__pyx_gilstate_save); \
} else { \
__pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__); \
}
#else
#define __Pyx_RefNannySetupContext(name, acquire_gil) \
__pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__)
#endif
#define __Pyx_RefNannyFinishContext() \
__Pyx_RefNanny->FinishContext(&__pyx_refnanny)
#define __Pyx_INCREF(r) __Pyx_RefNanny->INCREF(__pyx_refnanny, (PyObject *)(r), __LINE__)
#define __Pyx_DECREF(r) __Pyx_RefNanny->DECREF(__pyx_refnanny, (PyObject *)(r), __LINE__)
#define __Pyx_GOTREF(r) __Pyx_RefNanny->GOTREF(__pyx_refnanny, (PyObject *)(r), __LINE__)
#define __Pyx_GIVEREF(r) __Pyx_RefNanny->GIVEREF(__pyx_refnanny, (PyObject *)(r), __LINE__)
#define __Pyx_XINCREF(r) do { if((r) != NULL) {__Pyx_INCREF(r); }} while(0)
#define __Pyx_XDECREF(r) do { if((r) != NULL) {__Pyx_DECREF(r); }} while(0)
#define __Pyx_XGOTREF(r) do { if((r) != NULL) {__Pyx_GOTREF(r); }} while(0)
#define __Pyx_XGIVEREF(r) do { if((r) != NULL) {__Pyx_GIVEREF(r);}} while(0)
#else
#define __Pyx_RefNannyDeclarations
#define __Pyx_RefNannySetupContext(name, acquire_gil)
#define __Pyx_RefNannyFinishContext()
#define __Pyx_INCREF(r) Py_INCREF(r)
#define __Pyx_DECREF(r) Py_DECREF(r)
#define __Pyx_GOTREF(r)
#define __Pyx_GIVEREF(r)
#define __Pyx_XINCREF(r) Py_XINCREF(r)
#define __Pyx_XDECREF(r) Py_XDECREF(r)
#define __Pyx_XGOTREF(r)
#define __Pyx_XGIVEREF(r)
#endif /* CYTHON_REFNANNY */
#define __Pyx_XDECREF_SET(r, v) do { \
PyObject *tmp = (PyObject *) r; \
r = v; __Pyx_XDECREF(tmp); \
} while (0)
#define __Pyx_DECREF_SET(r, v) do { \
PyObject *tmp = (PyObject *) r; \
r = v; __Pyx_DECREF(tmp); \
} while (0)
#define __Pyx_CLEAR(r) do { PyObject* tmp = ((PyObject*)(r)); r = NULL; __Pyx_DECREF(tmp);} while(0)
#define __Pyx_XCLEAR(r) do { if((r) != NULL) {PyObject* tmp = ((PyObject*)(r)); r = NULL; __Pyx_DECREF(tmp);}} while(0)
#if CYTHON_COMPILING_IN_CPYTHON
static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) {
PyTypeObject* tp = Py_TYPE(obj);
if (likely(tp->tp_getattro))
return tp->tp_getattro(obj, attr_name);
#if PY_MAJOR_VERSION < 3
if (likely(tp->tp_getattr))
return tp->tp_getattr(obj, PyString_AS_STRING(attr_name));
#endif
return PyObject_GetAttr(obj, attr_name);
}
#else
#define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n)
#endif
static PyObject *__Pyx_GetBuiltinName(PyObject *name); /*proto*/
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected);
static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index);
static CYTHON_INLINE int __Pyx_IterFinish(void); /*proto*/
static int __Pyx_IternextUnpackEndCheck(PyObject *retval, Py_ssize_t expected); /*proto*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static CYTHON_INLINE int __Pyx_ArgTypeTest(PyObject *obj, PyTypeObject *type, int none_allowed,
const char *name, int exact); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
#include <string.h>
static CYTHON_INLINE int __Pyx_PyBytes_Equals(PyObject* s1, PyObject* s2, int equals); /*proto*/
static CYTHON_INLINE int __Pyx_PyUnicode_Equals(PyObject* s1, PyObject* s2, int equals); /*proto*/
static void __Pyx_RaiseArgtupleInvalid(const char* func_name, int exact,
Py_ssize_t num_min, Py_ssize_t num_max, Py_ssize_t num_found); /*proto*/
static void __Pyx_RaiseDoubleKeywordsError(const char* func_name, PyObject* kw_name); /*proto*/
static int __Pyx_ParseOptionalKeywords(PyObject *kwds, PyObject **argnames[], \
PyObject *kwds2, PyObject *values[], Py_ssize_t num_pos_args, \
const char* function_name); /*proto*/
static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name); /*proto*/
#define __Pyx_GetItemInt(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck) \
(__Pyx_fits_Py_ssize_t(i, type, is_signed) ? \
__Pyx_GetItemInt_Fast(o, (Py_ssize_t)i, is_list, wraparound, boundscheck) : \
(is_list ? (PyErr_SetString(PyExc_IndexError, "list index out of range"), (PyObject*)NULL) : \
__Pyx_GetItemInt_Generic(o, to_py_func(i))))
#define __Pyx_GetItemInt_List(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck) \
(__Pyx_fits_Py_ssize_t(i, type, is_signed) ? \
__Pyx_GetItemInt_List_Fast(o, (Py_ssize_t)i, wraparound, boundscheck) : \
(PyErr_SetString(PyExc_IndexError, "list index out of range"), (PyObject*)NULL))
static CYTHON_INLINE PyObject *__Pyx_GetItemInt_List_Fast(PyObject *o, Py_ssize_t i,
int wraparound, int boundscheck);
#define __Pyx_GetItemInt_Tuple(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck) \
(__Pyx_fits_Py_ssize_t(i, type, is_signed) ? \
__Pyx_GetItemInt_Tuple_Fast(o, (Py_ssize_t)i, wraparound, boundscheck) : \
(PyErr_SetString(PyExc_IndexError, "tuple index out of range"), (PyObject*)NULL))
static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Tuple_Fast(PyObject *o, Py_ssize_t i,
int wraparound, int boundscheck);
static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j);
static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i,
int is_list, int wraparound, int boundscheck);
#if CYTHON_COMPILING_IN_CPYTHON
static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg, PyObject *kw); /*proto*/
#else
#define __Pyx_PyObject_Call(func, arg, kw) PyObject_Call(func, arg, kw)
#endif
static CYTHON_INLINE void __Pyx_ErrRestore(PyObject *type, PyObject *value, PyObject *tb); /*proto*/
static CYTHON_INLINE void __Pyx_ErrFetch(PyObject **type, PyObject **value, PyObject **tb); /*proto*/
static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause); /*proto*/
#define __Pyx_GetItemInt_Unicode(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck) \
(__Pyx_fits_Py_ssize_t(i, type, is_signed) ? \
__Pyx_GetItemInt_Unicode_Fast(o, (Py_ssize_t)i, wraparound, boundscheck) : \
(PyErr_SetString(PyExc_IndexError, "string index out of range"), (Py_UCS4)-1))
static CYTHON_INLINE Py_UCS4 __Pyx_GetItemInt_Unicode_Fast(PyObject* ustring, Py_ssize_t i,
int wraparound, int boundscheck);
static CYTHON_INLINE PyObject* __Pyx_PyUnicode_Substring(
PyObject* text, Py_ssize_t start, Py_ssize_t stop);
#define __Pyx_SetItemInt(o, i, v, type, is_signed, to_py_func, is_list, wraparound, boundscheck) \
(__Pyx_fits_Py_ssize_t(i, type, is_signed) ? \
__Pyx_SetItemInt_Fast(o, (Py_ssize_t)i, v, is_list, wraparound, boundscheck) : \
(is_list ? (PyErr_SetString(PyExc_IndexError, "list assignment index out of range"), -1) : \
__Pyx_SetItemInt_Generic(o, to_py_func(i), v)))
static CYTHON_INLINE int __Pyx_SetItemInt_Generic(PyObject *o, PyObject *j, PyObject *v);
static CYTHON_INLINE int __Pyx_SetItemInt_Fast(PyObject *o, Py_ssize_t i, PyObject *v,
int is_list, int wraparound, int boundscheck);
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static int __Pyx_PyUnicode_Tailmatch(PyObject* s, PyObject* substr,
Py_ssize_t start, Py_ssize_t end, int direction) {
if (unlikely(PyTuple_Check(substr))) {
Py_ssize_t i, count = PyTuple_GET_SIZE(substr);
for (i = 0; i < count; i++) {
int result;
#if CYTHON_COMPILING_IN_CPYTHON
result = PyUnicode_Tailmatch(s, PyTuple_GET_ITEM(substr, i),
start, end, direction);
#else
PyObject* sub = PySequence_GetItem(substr, i);
if (unlikely(!sub)) return -1;
result = PyUnicode_Tailmatch(s, sub, start, end, direction);
Py_DECREF(sub);
#endif
if (result) {
return result;
}
}
return 0;
}
return PyUnicode_Tailmatch(s, substr, start, end, direction);
}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static void __Pyx_WriteUnraisable(const char *name, int clineno,
int lineno, const char *filename,
int full_traceback); /*proto*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
#if CYTHON_COMPILING_IN_CPYTHON
static CYTHON_INLINE int __Pyx_ListComp_Append(PyObject* list, PyObject* x) {
PyListObject* L = (PyListObject*) list;
Py_ssize_t len = Py_SIZE(list);
if (likely(L->allocated > len)) {
Py_INCREF(x);
PyList_SET_ITEM(list, len, x);
Py_SIZE(list) = len+1;
return 0;
}
return PyList_Append(list, x);
}
#else
#define __Pyx_ListComp_Append(L,x) PyList_Append(L,x)
#endif
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name); /*proto*/
static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *);
static CYTHON_INLINE uint64_t __Pyx_PyInt_As_uint64_t(PyObject *);
static CYTHON_INLINE size_t __Pyx_PyInt_As_size_t(PyObject *);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
#ifndef __Pyx_CppExn2PyErr
#include <new>
#include <typeinfo>
#include <stdexcept>
#include <ios>
static void __Pyx_CppExn2PyErr() {
try {
if (PyErr_Occurred())
; // let the latest Python exn pass through and ignore the current one
else
throw;
} catch (const std::bad_alloc& exn) {
PyErr_SetString(PyExc_MemoryError, exn.what());
} catch (const std::bad_cast& exn) {
PyErr_SetString(PyExc_TypeError, exn.what());
} catch (const std::domain_error& exn) {
PyErr_SetString(PyExc_ValueError, exn.what());
} catch (const std::invalid_argument& exn) {
PyErr_SetString(PyExc_ValueError, exn.what());
} catch (const std::ios_base::failure& exn) {
PyErr_SetString(PyExc_IOError, exn.what());
} catch (const std::out_of_range& exn) {
PyErr_SetString(PyExc_IndexError, exn.what());
} catch (const std::overflow_error& exn) {
PyErr_SetString(PyExc_OverflowError, exn.what());
} catch (const std::range_error& exn) {
PyErr_SetString(PyExc_ArithmeticError, exn.what());
} catch (const std::underflow_error& exn) {
PyErr_SetString(PyExc_ArithmeticError, exn.what());
} catch (const std::exception& exn) {
PyErr_SetString(PyExc_RuntimeError, exn.what());
}
catch (...)
{
PyErr_SetString(PyExc_RuntimeError, "Unknown exception");
}
}
#endif
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_uint64_t(uint64_t value);
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value);
static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *);
static int __Pyx_check_binary_version(void);
#if CYTHON_COMPILING_IN_CPYTHON
#define __Pyx_PyObject_DelAttrStr(o,n) __Pyx_PyObject_SetAttrStr(o,n,NULL)
static CYTHON_INLINE int __Pyx_PyObject_SetAttrStr(PyObject* obj, PyObject* attr_name, PyObject* value) {
PyTypeObject* tp = Py_TYPE(obj);
if (likely(tp->tp_setattro))
return tp->tp_setattro(obj, attr_name, value);
#if PY_MAJOR_VERSION < 3
if (likely(tp->tp_setattr))
return tp->tp_setattr(obj, PyString_AS_STRING(attr_name), value);
#endif
return PyObject_SetAttr(obj, attr_name, value);
}
#else
#define __Pyx_PyObject_DelAttrStr(o,n) PyObject_DelAttr(o,n)
#define __Pyx_PyObject_SetAttrStr(o,n,v) PyObject_SetAttr(o,n,v)
#endif
static int __Pyx_ExportVoidPtr(PyObject *name, void *p, const char *sig); /*proto*/
static int __Pyx_ExportFunction(const char *name, void (*f)(void), const char *sig); /*proto*/
typedef struct {
int code_line;
PyCodeObject* code_object;
} __Pyx_CodeObjectCacheEntry;
struct __Pyx_CodeObjectCache {
int count;
int max_count;
__Pyx_CodeObjectCacheEntry* entries;
};
static struct __Pyx_CodeObjectCache __pyx_code_cache = {0,0,NULL};
static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line);
static PyCodeObject *__pyx_find_code_object(int code_line);
static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object);
static void __Pyx_AddTraceback(const char *funcname, int c_line,
int py_line, const char *filename); /*proto*/
static int __Pyx_InitStrings(__Pyx_StringTabEntry *t); /*proto*/
/* Module declarations from 'libcpp.utility' */
/* Module declarations from 'libcpp.vector' */
/* Module declarations from 'libc.stdint' */
/* Module declarations from 'ext.sparsehash' */
/* Module declarations from 'spacy.lexeme' */
/* Module declarations from 'libc.string' */
/* Module declarations from 'libc.stdlib' */
/* Module declarations from 'ext.murmurhash' */
/* Module declarations from 'spacy.en' */
static google::dense_hash_map<__pyx_t_5spacy_6lexeme_StringHash,__pyx_t_5spacy_2en_Lexeme_ptr> __pyx_v_5spacy_2en_LEXEMES;
static struct __pyx_t_5spacy_6lexeme_Lexeme __pyx_v_5spacy_2en_BLANK_WORD;
static __pyx_t_5spacy_2en_Lexeme_addr __pyx_f_5spacy_2en_lookup(PyObject *, int __pyx_skip_dispatch); /*proto*/
static __pyx_t_5spacy_2en_Lexeme_addr __pyx_f_5spacy_2en_lookup_chunk(PyObject *, int, int, int __pyx_skip_dispatch); /*proto*/
static __pyx_t_5spacy_6lexeme_StringHash __pyx_f_5spacy_2en_hash_string(PyObject *, size_t); /*proto*/
static PyObject *__pyx_f_5spacy_2en_unhash(__pyx_t_5spacy_6lexeme_StringHash, int __pyx_skip_dispatch); /*proto*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static std::vector<__pyx_t_5spacy_2en_Lexeme_addr> __pyx_f_5spacy_2en_tokenize(PyObject *, int __pyx_skip_dispatch); /*proto*/
static CYTHON_INLINE int __pyx_f_5spacy_2en_is_whitespace(Py_UNICODE); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_f_5spacy_2en_normalize_word_string(PyObject *); /*proto*/
static PyObject *__pyx_f_5spacy_2en__substr(PyObject *, int, int, size_t, int __pyx_skip_dispatch); /*proto*/
static struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_f_5spacy_2en__add(__pyx_t_5spacy_6lexeme_StringHash, PyObject *, int, size_t); /*proto*/
static struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_f_5spacy_2en__init_lexeme(PyObject *, __pyx_t_5spacy_6lexeme_StringHash, int, size_t); /*proto*/
static size_t __pyx_f_5spacy_2en__find_split(PyObject *, size_t); /*proto*/
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static int __pyx_f_5spacy_2en_is_punct(PyObject *, size_t, size_t); /*proto*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr(const std::vector<__pyx_t_5spacy_2en_Lexeme_addr> &); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
#define __Pyx_MODULE_NAME "spacy.en"
int __pyx_module_is_main_spacy__en = 0;
/* Implementation of 'spacy.en' */
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_builtin_enumerate;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_builtin_range;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_builtin_ValueError;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_pf_5spacy_2en_load_tokenization(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_token_rules); /* proto */
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pf_5spacy_2en_2tokenize(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_string); /* proto */
static PyObject *__pyx_pf_5spacy_2en_4lookup(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_string); /* proto */
static PyObject *__pyx_pf_5spacy_2en_6lookup_chunk(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_string, int __pyx_v_start, int __pyx_v_end); /* proto */
static PyObject *__pyx_pf_5spacy_2en_8unhash(CYTHON_UNUSED PyObject *__pyx_self, __pyx_t_5spacy_6lexeme_StringHash __pyx_v_hash_value); /* proto */
static PyObject *__pyx_pf_5spacy_2en_10_substr(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_string, int __pyx_v_start, int __pyx_v_end, size_t __pyx_v_length); /* proto */
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_[] = "";
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static char __pyx_k_i[] = "i";
static char __pyx_k_s[] = "'s";
static char __pyx_k_en[] = "en";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_end[] = "end";
static char __pyx_k_lex[] = "lex";
static char __pyx_k_sic[] = "sic";
static char __pyx_k_YEAR[] = "!YEAR";
static char __pyx_k_main[] = "__main__";
static char __pyx_k_prob[] = "prob";
static char __pyx_k_tail[] = "tail";
static char __pyx_k_test[] = "__test__";
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static char __pyx_k_util[] = "util";
static char __pyx_k_word[] = "word";
static char __pyx_k_chunk[] = "chunk";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_first[] = "first";
static char __pyx_k_last3[] = "last3";
static char __pyx_k_lower[] = "lower";
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static char __pyx_k_range[] = "range";
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static char __pyx_k_s_d_s[] = "%s:@:%d:@:%s";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_start[] = "start";
static char __pyx_k_DIGITS[] = "!DIGITS";
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static char __pyx_k_hashed[] = "hashed";
static char __pyx_k_import[] = "__import__";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_length[] = "length";
static char __pyx_k_normed[] = "normed";
static char __pyx_k_string[] = "string";
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static char __pyx_k_tokens[] = "tokens";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_LEXEMES[] = "LEXEMES";
static char __pyx_k_STRINGS[] = "STRINGS";
static char __pyx_k_cluster[] = "cluster";
static char __pyx_k_isdigit[] = "isdigit";
static char __pyx_k_pyx_capi[] = "__pyx_capi__";
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static char __pyx_k_spacy_en[] = "spacy.en";
static char __pyx_k_enumerate[] = "enumerate";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_oft_title[] = "oft_title";
static char __pyx_k_oft_upper[] = "oft_upper";
static char __pyx_k_ValueError[] = "ValueError";
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static char __pyx_k_token_rules[] = "token_rules";
static char __pyx_k_token_string[] = "token_string";
static char __pyx_k_load_tokenization[] = "load_tokenization";
static char __pyx_k_read_tokenization[] = "read_tokenization";
static char __pyx_k_Users_matt_repos_spaCy_spacy_en[] = "/Users/matt/repos/spaCy/spacy/en.pyx";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_Serve_pointers_to_Lexeme_structs[] = "Serve pointers to Lexeme structs, given strings. Maintain a reverse index,\nso that strings can be retrieved from hashes. Use 64-bit hash values and\nboldly assume no collisions.\n";
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_s_;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_kp_u_;
static PyObject *__pyx_kp_u_DIGITS;
static PyObject *__pyx_n_s_LEXEMES;
static PyObject *__pyx_n_s_STRINGS;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_kp_s_Users_matt_repos_spaCy_spacy_en;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_ValueError;
static PyObject *__pyx_kp_u_YEAR;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_s_chunk;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_cluster;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_u_en;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_end;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_s_enumerate;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_first;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_s_hashed;
static PyObject *__pyx_n_s_i;
static PyObject *__pyx_n_s_import;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_isdigit;
static PyObject *__pyx_n_s_last3;
static PyObject *__pyx_n_s_length;
static PyObject *__pyx_n_s_lex;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_s_load_tokenization;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_lower;
static PyObject *__pyx_n_s_main;
static PyObject *__pyx_n_s_normed;
static PyObject *__pyx_n_s_oft_title;
static PyObject *__pyx_n_s_oft_upper;
static PyObject *__pyx_n_s_prob;
static PyObject *__pyx_n_s_pyx_capi;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_n_s_range;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_s_read_tokenization;
static PyObject *__pyx_kp_u_s;
static PyObject *__pyx_kp_u_s_d_s;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_sic;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_s_spacy_en;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_start;
static PyObject *__pyx_n_s_string;
static PyObject *__pyx_n_s_tail;
static PyObject *__pyx_n_s_test;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject *__pyx_n_s_token_rules;
static PyObject *__pyx_n_s_token_string;
static PyObject *__pyx_n_s_tokens;
static PyObject *__pyx_n_s_util;
static PyObject *__pyx_n_s_word;
static PyObject *__pyx_int_0;
static PyObject *__pyx_int_1;
static PyObject *__pyx_tuple__2;
static PyObject *__pyx_tuple__4;
static PyObject *__pyx_codeobj__3;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":25
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* def load_tokenization(token_rules): # <<<<<<<<<<<<<<
* cdef Lexeme* word
* cdef StringHash hashed
*/
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_2en_1load_tokenization(PyObject *__pyx_self, PyObject *__pyx_v_token_rules); /*proto*/
static PyMethodDef __pyx_mdef_5spacy_2en_1load_tokenization = {__Pyx_NAMESTR("load_tokenization"), (PyCFunction)__pyx_pw_5spacy_2en_1load_tokenization, METH_O, __Pyx_DOCSTR(0)};
static PyObject *__pyx_pw_5spacy_2en_1load_tokenization(PyObject *__pyx_self, PyObject *__pyx_v_token_rules) {
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("load_tokenization (wrapper)", 0);
__pyx_r = __pyx_pf_5spacy_2en_load_tokenization(__pyx_self, ((PyObject *)__pyx_v_token_rules));
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_2en_load_tokenization(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_token_rules) {
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_v_word;
__pyx_t_5spacy_6lexeme_StringHash __pyx_v_hashed;
PyObject *__pyx_v_chunk = NULL;
PyObject *__pyx_v_lex = NULL;
PyObject *__pyx_v_tokens = NULL;
PyObject *__pyx_v_i = NULL;
PyObject *__pyx_v_token_string = NULL;
Py_ssize_t __pyx_v_length;
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
PyObject *__pyx_t_1 = NULL;
Py_ssize_t __pyx_t_2;
PyObject *(*__pyx_t_3)(PyObject *);
PyObject *__pyx_t_4 = NULL;
PyObject *__pyx_t_5 = NULL;
PyObject *__pyx_t_6 = NULL;
PyObject *__pyx_t_7 = NULL;
PyObject *__pyx_t_8 = NULL;
PyObject *(*__pyx_t_9)(PyObject *);
Py_ssize_t __pyx_t_10;
__pyx_t_5spacy_6lexeme_StringHash __pyx_t_11;
Py_ssize_t __pyx_t_12;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_t_13;
PyObject *(*__pyx_t_14)(PyObject *);
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("load_tokenization", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":28
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* cdef Lexeme* word
* cdef StringHash hashed
* for chunk, lex, tokens in token_rules: # <<<<<<<<<<<<<<
* hashed = hash_string(chunk, len(chunk))
* assert LEXEMES[hashed] == NULL
*/
if (PyList_CheckExact(__pyx_v_token_rules) || PyTuple_CheckExact(__pyx_v_token_rules)) {
__pyx_t_1 = __pyx_v_token_rules; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0;
__pyx_t_3 = NULL;
} else {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_token_rules); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_t_3 = Py_TYPE(__pyx_t_1)->tp_iternext;
}
for (;;) {
if (!__pyx_t_3 && PyList_CheckExact(__pyx_t_1)) {
if (__pyx_t_2 >= PyList_GET_SIZE(__pyx_t_1)) break;
#if CYTHON_COMPILING_IN_CPYTHON
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely(0 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
#else
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
#endif
} else if (!__pyx_t_3 && PyTuple_CheckExact(__pyx_t_1)) {
if (__pyx_t_2 >= PyTuple_GET_SIZE(__pyx_t_1)) break;
#if CYTHON_COMPILING_IN_CPYTHON
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely(0 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
#else
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
#endif
} else {
__pyx_t_4 = __pyx_t_3(__pyx_t_1);
if (unlikely(!__pyx_t_4)) {
PyObject* exc_type = PyErr_Occurred();
if (exc_type) {
if (likely(exc_type == PyExc_StopIteration || PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear();
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
else {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
}
break;
}
__Pyx_GOTREF(__pyx_t_4);
}
if ((likely(PyTuple_CheckExact(__pyx_t_4))) || (PyList_CheckExact(__pyx_t_4))) {
PyObject* sequence = __pyx_t_4;
#if CYTHON_COMPILING_IN_CPYTHON
Py_ssize_t size = Py_SIZE(sequence);
#else
Py_ssize_t size = PySequence_Size(sequence);
#endif
if (unlikely(size != 3)) {
if (size > 3) __Pyx_RaiseTooManyValuesError(3);
else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
}
#if CYTHON_COMPILING_IN_CPYTHON
if (likely(PyTuple_CheckExact(sequence))) {
__pyx_t_5 = PyTuple_GET_ITEM(sequence, 0);
__pyx_t_6 = PyTuple_GET_ITEM(sequence, 1);
__pyx_t_7 = PyTuple_GET_ITEM(sequence, 2);
} else {
__pyx_t_5 = PyList_GET_ITEM(sequence, 0);
__pyx_t_6 = PyList_GET_ITEM(sequence, 1);
__pyx_t_7 = PyList_GET_ITEM(sequence, 2);
}
__Pyx_INCREF(__pyx_t_5);
__Pyx_INCREF(__pyx_t_6);
__Pyx_INCREF(__pyx_t_7);
#else
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_5 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_5)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_5);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_6);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_7 = PySequence_ITEM(sequence, 2); if (unlikely(!__pyx_t_7)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_7);
#endif
__Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
} else {
Py_ssize_t index = -1;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_8 = PyObject_GetIter(__pyx_t_4); if (unlikely(!__pyx_t_8)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_8);
__Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
__pyx_t_9 = Py_TYPE(__pyx_t_8)->tp_iternext;
index = 0; __pyx_t_5 = __pyx_t_9(__pyx_t_8); if (unlikely(!__pyx_t_5)) goto __pyx_L5_unpacking_failed;
__Pyx_GOTREF(__pyx_t_5);
index = 1; __pyx_t_6 = __pyx_t_9(__pyx_t_8); if (unlikely(!__pyx_t_6)) goto __pyx_L5_unpacking_failed;
__Pyx_GOTREF(__pyx_t_6);
index = 2; __pyx_t_7 = __pyx_t_9(__pyx_t_8); if (unlikely(!__pyx_t_7)) goto __pyx_L5_unpacking_failed;
__Pyx_GOTREF(__pyx_t_7);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (__Pyx_IternextUnpackEndCheck(__pyx_t_9(__pyx_t_8), 3) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_t_9 = NULL;
__Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0;
goto __pyx_L6_unpacking_done;
__pyx_L5_unpacking_failed:;
__Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0;
__pyx_t_9 = NULL;
if (__Pyx_IterFinish() == 0) __Pyx_RaiseNeedMoreValuesError(index);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_L6_unpacking_done:;
}
__Pyx_XDECREF_SET(__pyx_v_chunk, __pyx_t_5);
__pyx_t_5 = 0;
__Pyx_XDECREF_SET(__pyx_v_lex, __pyx_t_6);
__pyx_t_6 = 0;
__Pyx_XDECREF_SET(__pyx_v_tokens, __pyx_t_7);
__pyx_t_7 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":29
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* cdef StringHash hashed
* for chunk, lex, tokens in token_rules:
* hashed = hash_string(chunk, len(chunk)) # <<<<<<<<<<<<<<
* assert LEXEMES[hashed] == NULL
* word = _add(hashed, lex, len(lex), len(lex))
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (!(likely(PyUnicode_CheckExact(__pyx_v_chunk))||((__pyx_v_chunk) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "unicode", Py_TYPE(__pyx_v_chunk)->tp_name), 0))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 29; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_10 = PyObject_Length(__pyx_v_chunk); if (unlikely(__pyx_t_10 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 29; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_11 = __pyx_f_5spacy_2en_hash_string(((PyObject*)__pyx_v_chunk), __pyx_t_10); if (unlikely(__pyx_t_11 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 29; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_v_hashed = __pyx_t_11;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":30
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* for chunk, lex, tokens in token_rules:
* hashed = hash_string(chunk, len(chunk))
* assert LEXEMES[hashed] == NULL # <<<<<<<<<<<<<<
* word = _add(hashed, lex, len(lex), len(lex))
* for i, lex in enumerate(tokens):
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
if (unlikely(!(((__pyx_v_5spacy_2en_LEXEMES[__pyx_v_hashed]) == NULL) != 0))) {
PyErr_SetNone(PyExc_AssertionError);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 30; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
}
}
#endif
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":31
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* hashed = hash_string(chunk, len(chunk))
* assert LEXEMES[hashed] == NULL
* word = _add(hashed, lex, len(lex), len(lex)) # <<<<<<<<<<<<<<
* for i, lex in enumerate(tokens):
* token_string = '%s:@:%d:@:%s' % (chunk, i, lex)
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (!(likely(PyUnicode_CheckExact(__pyx_v_lex))||((__pyx_v_lex) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "unicode", Py_TYPE(__pyx_v_lex)->tp_name), 0))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 31; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_10 = PyObject_Length(__pyx_v_lex); if (unlikely(__pyx_t_10 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 31; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_12 = PyObject_Length(__pyx_v_lex); if (unlikely(__pyx_t_12 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 31; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_13 = __pyx_f_5spacy_2en__add(__pyx_v_hashed, ((PyObject*)__pyx_v_lex), __pyx_t_10, __pyx_t_12); if (unlikely(__pyx_t_13 == NULL)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 31; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_v_word = __pyx_t_13;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":32
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* assert LEXEMES[hashed] == NULL
* word = _add(hashed, lex, len(lex), len(lex))
* for i, lex in enumerate(tokens): # <<<<<<<<<<<<<<
* token_string = '%s:@:%d:@:%s' % (chunk, i, lex)
* length = len(token_string)
*/
__Pyx_INCREF(__pyx_int_0);
__pyx_t_4 = __pyx_int_0;
if (PyList_CheckExact(__pyx_v_tokens) || PyTuple_CheckExact(__pyx_v_tokens)) {
__pyx_t_7 = __pyx_v_tokens; __Pyx_INCREF(__pyx_t_7); __pyx_t_12 = 0;
__pyx_t_14 = NULL;
} else {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_12 = -1; __pyx_t_7 = PyObject_GetIter(__pyx_v_tokens); if (unlikely(!__pyx_t_7)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 32; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_7);
__pyx_t_14 = Py_TYPE(__pyx_t_7)->tp_iternext;
}
for (;;) {
if (!__pyx_t_14 && PyList_CheckExact(__pyx_t_7)) {
if (__pyx_t_12 >= PyList_GET_SIZE(__pyx_t_7)) break;
#if CYTHON_COMPILING_IN_CPYTHON
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = PyList_GET_ITEM(__pyx_t_7, __pyx_t_12); __Pyx_INCREF(__pyx_t_6); __pyx_t_12++; if (unlikely(0 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 32; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
#else
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = PySequence_ITEM(__pyx_t_7, __pyx_t_12); __pyx_t_12++; if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 32; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
#endif
} else if (!__pyx_t_14 && PyTuple_CheckExact(__pyx_t_7)) {
if (__pyx_t_12 >= PyTuple_GET_SIZE(__pyx_t_7)) break;
#if CYTHON_COMPILING_IN_CPYTHON
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = PyTuple_GET_ITEM(__pyx_t_7, __pyx_t_12); __Pyx_INCREF(__pyx_t_6); __pyx_t_12++; if (unlikely(0 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 32; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
#else
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = PySequence_ITEM(__pyx_t_7, __pyx_t_12); __pyx_t_12++; if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 32; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
#endif
} else {
__pyx_t_6 = __pyx_t_14(__pyx_t_7);
if (unlikely(!__pyx_t_6)) {
PyObject* exc_type = PyErr_Occurred();
if (exc_type) {
if (likely(exc_type == PyExc_StopIteration || PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear();
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
else {__pyx_filename = __pyx_f[0]; __pyx_lineno = 32; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
}
break;
}
__Pyx_GOTREF(__pyx_t_6);
}
__Pyx_DECREF_SET(__pyx_v_lex, __pyx_t_6);
__pyx_t_6 = 0;
__Pyx_INCREF(__pyx_t_4);
__Pyx_XDECREF_SET(__pyx_v_i, __pyx_t_4);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = PyNumber_Add(__pyx_t_4, __pyx_int_1); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 32; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_6);
__Pyx_DECREF(__pyx_t_4);
__pyx_t_4 = __pyx_t_6;
__pyx_t_6 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":33
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* word = _add(hashed, lex, len(lex), len(lex))
* for i, lex in enumerate(tokens):
* token_string = '%s:@:%d:@:%s' % (chunk, i, lex) # <<<<<<<<<<<<<<
* length = len(token_string)
* hashed = hash_string(token_string, length)
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = PyTuple_New(3); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 33; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_6);
__Pyx_INCREF(__pyx_v_chunk);
PyTuple_SET_ITEM(__pyx_t_6, 0, __pyx_v_chunk);
__Pyx_GIVEREF(__pyx_v_chunk);
__Pyx_INCREF(__pyx_v_i);
PyTuple_SET_ITEM(__pyx_t_6, 1, __pyx_v_i);
__Pyx_GIVEREF(__pyx_v_i);
__Pyx_INCREF(__pyx_v_lex);
PyTuple_SET_ITEM(__pyx_t_6, 2, __pyx_v_lex);
__Pyx_GIVEREF(__pyx_v_lex);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_5 = PyUnicode_Format(__pyx_kp_u_s_d_s, __pyx_t_6); if (unlikely(!__pyx_t_5)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 33; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_5);
__Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0;
__Pyx_XDECREF_SET(__pyx_v_token_string, ((PyObject*)__pyx_t_5));
__pyx_t_5 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":34
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* for i, lex in enumerate(tokens):
* token_string = '%s:@:%d:@:%s' % (chunk, i, lex)
* length = len(token_string) # <<<<<<<<<<<<<<
* hashed = hash_string(token_string, length)
* word.tail = _add(hashed, lex, 0, len(lex))
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_10 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_token_string); if (unlikely(__pyx_t_10 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 34; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_v_length = __pyx_t_10;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":35
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* token_string = '%s:@:%d:@:%s' % (chunk, i, lex)
* length = len(token_string)
* hashed = hash_string(token_string, length) # <<<<<<<<<<<<<<
* word.tail = _add(hashed, lex, 0, len(lex))
* word = word.tail
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_11 = __pyx_f_5spacy_2en_hash_string(__pyx_v_token_string, __pyx_v_length); if (unlikely(__pyx_t_11 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 35; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_v_hashed = __pyx_t_11;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":36
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* length = len(token_string)
* hashed = hash_string(token_string, length)
* word.tail = _add(hashed, lex, 0, len(lex)) # <<<<<<<<<<<<<<
* word = word.tail
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (!(likely(PyUnicode_CheckExact(__pyx_v_lex))||((__pyx_v_lex) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "unicode", Py_TYPE(__pyx_v_lex)->tp_name), 0))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 36; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_10 = PyObject_Length(__pyx_v_lex); if (unlikely(__pyx_t_10 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 36; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_13 = __pyx_f_5spacy_2en__add(__pyx_v_hashed, ((PyObject*)__pyx_v_lex), 0, __pyx_t_10); if (unlikely(__pyx_t_13 == NULL)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 36; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_v_word->tail = __pyx_t_13;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":37
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* hashed = hash_string(token_string, length)
* word.tail = _add(hashed, lex, 0, len(lex))
* word = word.tail # <<<<<<<<<<<<<<
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*/
__pyx_t_13 = __pyx_v_word->tail;
__pyx_v_word = __pyx_t_13;
}
__Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0;
__Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
}
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":25
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* def load_tokenization(token_rules): # <<<<<<<<<<<<<<
* cdef Lexeme* word
* cdef StringHash hashed
*/
/* function exit code */
__pyx_r = Py_None; __Pyx_INCREF(Py_None);
goto __pyx_L0;
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_XDECREF(__pyx_t_4);
__Pyx_XDECREF(__pyx_t_5);
__Pyx_XDECREF(__pyx_t_6);
__Pyx_XDECREF(__pyx_t_7);
__Pyx_XDECREF(__pyx_t_8);
__Pyx_AddTraceback("spacy.en.load_tokenization", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XDECREF(__pyx_v_chunk);
__Pyx_XDECREF(__pyx_v_lex);
__Pyx_XDECREF(__pyx_v_tokens);
__Pyx_XDECREF(__pyx_v_i);
__Pyx_XDECREF(__pyx_v_token_string);
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":43
*
*
* cpdef vector[Lexeme_addr] tokenize(unicode string) except *: # <<<<<<<<<<<<<<
* cdef size_t length = len(string)
* cdef Py_UNICODE* characters = <Py_UNICODE*>string
*/
static PyObject *__pyx_pw_5spacy_2en_3tokenize(PyObject *__pyx_self, PyObject *__pyx_v_string); /*proto*/
static std::vector<__pyx_t_5spacy_2en_Lexeme_addr> __pyx_f_5spacy_2en_tokenize(PyObject *__pyx_v_string, CYTHON_UNUSED int __pyx_skip_dispatch) {
size_t __pyx_v_length;
Py_UNICODE *__pyx_v_characters;
size_t __pyx_v_i;
Py_UNICODE __pyx_v_c;
std::vector<__pyx_t_5spacy_2en_Lexeme_addr> __pyx_v_tokens;
PyObject *__pyx_v_current = 0;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_v_token;
std::vector<__pyx_t_5spacy_2en_Lexeme_addr> __pyx_r;
__Pyx_RefNannyDeclarations
Py_ssize_t __pyx_t_1;
Py_UNICODE *__pyx_t_2;
std::vector<__pyx_t_5spacy_2en_Lexeme_addr> __pyx_t_3;
size_t __pyx_t_4;
size_t __pyx_t_5;
int __pyx_t_6;
__pyx_t_5spacy_2en_Lexeme_addr __pyx_t_7;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_t_8;
PyObject *__pyx_t_9 = NULL;
PyObject *__pyx_t_10 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("tokenize", 0);
/* "spacy/en.pyx":44
*
* cpdef vector[Lexeme_addr] tokenize(unicode string) except *:
* cdef size_t length = len(string) # <<<<<<<<<<<<<<
* cdef Py_UNICODE* characters = <Py_UNICODE*>string
*
*/
if (unlikely(__pyx_v_string == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 44; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
__pyx_t_1 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_string); if (unlikely(__pyx_t_1 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 44; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_v_length = __pyx_t_1;
/* "spacy/en.pyx":45
* cpdef vector[Lexeme_addr] tokenize(unicode string) except *:
* cdef size_t length = len(string)
* cdef Py_UNICODE* characters = <Py_UNICODE*>string # <<<<<<<<<<<<<<
*
* cdef size_t i
*/
__pyx_t_2 = __Pyx_PyUnicode_AsUnicode(__pyx_v_string); if (unlikely((!__pyx_t_2) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 45; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_v_characters = ((Py_UNICODE *)__pyx_t_2);
/* "spacy/en.pyx":50
* cdef Py_UNICODE c
*
* cdef vector[Lexeme_addr] tokens = vector[Lexeme_addr]() # <<<<<<<<<<<<<<
* cdef unicode current = u''
* cdef Lexeme* token
*/
try {
__pyx_t_3 = std::vector<__pyx_t_5spacy_2en_Lexeme_addr>();
} catch(...) {
__Pyx_CppExn2PyErr();
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 50; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
__pyx_v_tokens = __pyx_t_3;
/* "spacy/en.pyx":51
*
* cdef vector[Lexeme_addr] tokens = vector[Lexeme_addr]()
* cdef unicode current = u'' # <<<<<<<<<<<<<<
* cdef Lexeme* token
* for i in range(length):
*/
__Pyx_INCREF(__pyx_kp_u_);
__pyx_v_current = __pyx_kp_u_;
/* "spacy/en.pyx":53
* cdef unicode current = u''
* cdef Lexeme* token
* for i in range(length): # <<<<<<<<<<<<<<
* c = characters[i]
* if is_whitespace(c):
*/
__pyx_t_4 = __pyx_v_length;
for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) {
__pyx_v_i = __pyx_t_5;
/* "spacy/en.pyx":54
* cdef Lexeme* token
* for i in range(length):
* c = characters[i] # <<<<<<<<<<<<<<
* if is_whitespace(c):
* if current:
*/
__pyx_v_c = (__pyx_v_characters[__pyx_v_i]);
/* "spacy/en.pyx":55
* for i in range(length):
* c = characters[i]
* if is_whitespace(c): # <<<<<<<<<<<<<<
* if current:
* token = <Lexeme*>lookup(current)
*/
__pyx_t_6 = (__pyx_f_5spacy_2en_is_whitespace(__pyx_v_c) != 0);
if (__pyx_t_6) {
/* "spacy/en.pyx":56
* c = characters[i]
* if is_whitespace(c):
* if current: # <<<<<<<<<<<<<<
* token = <Lexeme*>lookup(current)
* while token != NULL:
*/
__pyx_t_6 = (__pyx_v_current != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_current) != 0);
if (__pyx_t_6) {
/* "spacy/en.pyx":57
* if is_whitespace(c):
* if current:
* token = <Lexeme*>lookup(current) # <<<<<<<<<<<<<<
* while token != NULL:
* tokens.push_back(<Lexeme_addr>token)
*/
__pyx_t_7 = __pyx_f_5spacy_2en_lookup(__pyx_v_current, 0); if (unlikely(__pyx_t_7 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 57; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_v_token = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_t_7);
/* "spacy/en.pyx":58
* if current:
* token = <Lexeme*>lookup(current)
* while token != NULL: # <<<<<<<<<<<<<<
* tokens.push_back(<Lexeme_addr>token)
* token = token.tail
*/
while (1) {
__pyx_t_6 = ((__pyx_v_token != NULL) != 0);
if (!__pyx_t_6) break;
/* "spacy/en.pyx":59
* token = <Lexeme*>lookup(current)
* while token != NULL:
* tokens.push_back(<Lexeme_addr>token) # <<<<<<<<<<<<<<
* token = token.tail
* current = u''
*/
__pyx_v_tokens.push_back(((__pyx_t_5spacy_2en_Lexeme_addr)__pyx_v_token));
/* "spacy/en.pyx":60
* while token != NULL:
* tokens.push_back(<Lexeme_addr>token)
* token = token.tail # <<<<<<<<<<<<<<
* current = u''
* else:
*/
__pyx_t_8 = __pyx_v_token->tail;
__pyx_v_token = __pyx_t_8;
}
goto __pyx_L6;
}
__pyx_L6:;
/* "spacy/en.pyx":61
* tokens.push_back(<Lexeme_addr>token)
* token = token.tail
* current = u'' # <<<<<<<<<<<<<<
* else:
* current += c
*/
__Pyx_INCREF(__pyx_kp_u_);
__Pyx_DECREF_SET(__pyx_v_current, __pyx_kp_u_);
goto __pyx_L5;
}
/*else*/ {
/* "spacy/en.pyx":63
* current = u''
* else:
* current += c # <<<<<<<<<<<<<<
* if current:
* token = <Lexeme*>lookup(current)
*/
__pyx_t_9 = PyUnicode_FromOrdinal(__pyx_v_c); if (unlikely(!__pyx_t_9)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_9);
__pyx_t_10 = __Pyx_PyUnicode_ConcatSafe(__pyx_v_current, __pyx_t_9); if (unlikely(!__pyx_t_10)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 63; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_10);
__Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0;
__Pyx_DECREF_SET(__pyx_v_current, ((PyObject*)__pyx_t_10));
__pyx_t_10 = 0;
}
__pyx_L5:;
}
/* "spacy/en.pyx":64
* else:
* current += c
* if current: # <<<<<<<<<<<<<<
* token = <Lexeme*>lookup(current)
* while token != NULL:
*/
__pyx_t_6 = (__pyx_v_current != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_current) != 0);
if (__pyx_t_6) {
/* "spacy/en.pyx":65
* current += c
* if current:
* token = <Lexeme*>lookup(current) # <<<<<<<<<<<<<<
* while token != NULL:
* tokens.push_back(<Lexeme_addr>token)
*/
__pyx_t_7 = __pyx_f_5spacy_2en_lookup(__pyx_v_current, 0); if (unlikely(__pyx_t_7 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 65; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_v_token = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_t_7);
/* "spacy/en.pyx":66
* if current:
* token = <Lexeme*>lookup(current)
* while token != NULL: # <<<<<<<<<<<<<<
* tokens.push_back(<Lexeme_addr>token)
* token = token.tail
*/
while (1) {
__pyx_t_6 = ((__pyx_v_token != NULL) != 0);
if (!__pyx_t_6) break;
/* "spacy/en.pyx":67
* token = <Lexeme*>lookup(current)
* while token != NULL:
* tokens.push_back(<Lexeme_addr>token) # <<<<<<<<<<<<<<
* token = token.tail
* return tokens
*/
__pyx_v_tokens.push_back(((__pyx_t_5spacy_2en_Lexeme_addr)__pyx_v_token));
/* "spacy/en.pyx":68
* while token != NULL:
* tokens.push_back(<Lexeme_addr>token)
* token = token.tail # <<<<<<<<<<<<<<
* return tokens
*
*/
__pyx_t_8 = __pyx_v_token->tail;
__pyx_v_token = __pyx_t_8;
}
goto __pyx_L9;
}
__pyx_L9:;
/* "spacy/en.pyx":69
* tokens.push_back(<Lexeme_addr>token)
* token = token.tail
* return tokens # <<<<<<<<<<<<<<
*
* cdef inline bint is_whitespace(Py_UNICODE c):
*/
__pyx_r = __pyx_v_tokens;
goto __pyx_L0;
/* "spacy/en.pyx":43
*
*
* cpdef vector[Lexeme_addr] tokenize(unicode string) except *: # <<<<<<<<<<<<<<
* cdef size_t length = len(string)
* cdef Py_UNICODE* characters = <Py_UNICODE*>string
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_9);
__Pyx_XDECREF(__pyx_t_10);
__Pyx_AddTraceback("spacy.en.tokenize", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_L0:;
__Pyx_XDECREF(__pyx_v_current);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_2en_3tokenize(PyObject *__pyx_self, PyObject *__pyx_v_string); /*proto*/
static PyObject *__pyx_pw_5spacy_2en_3tokenize(PyObject *__pyx_self, PyObject *__pyx_v_string) {
CYTHON_UNUSED int __pyx_lineno = 0;
CYTHON_UNUSED const char *__pyx_filename = NULL;
CYTHON_UNUSED int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("tokenize (wrapper)", 0);
if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_string), (&PyUnicode_Type), 1, "string", 1))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 43; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_r = __pyx_pf_5spacy_2en_2tokenize(__pyx_self, ((PyObject*)__pyx_v_string));
/* function exit code */
goto __pyx_L0;
__pyx_L1_error:;
__pyx_r = NULL;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_2en_2tokenize(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_string) {
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
std::vector<__pyx_t_5spacy_2en_Lexeme_addr> __pyx_t_1;
PyObject *__pyx_t_2 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("tokenize", 0);
__Pyx_XDECREF(__pyx_r);
__pyx_t_1 = __pyx_f_5spacy_2en_tokenize(__pyx_v_string, 0); if (unlikely(PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 43; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_2 = __pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr(__pyx_t_1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 43; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_2);
__pyx_r = __pyx_t_2;
__pyx_t_2 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_2);
__Pyx_AddTraceback("spacy.en.tokenize", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* "spacy/en.pyx":71
* return tokens
*
* cdef inline bint is_whitespace(Py_UNICODE c): # <<<<<<<<<<<<<<
* # TODO: Support other unicode spaces
* # https://www.cs.tut.fi/~jkorpela/chars/spaces.html
*/
static CYTHON_INLINE int __pyx_f_5spacy_2en_is_whitespace(Py_UNICODE __pyx_v_c) {
int __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("is_whitespace", 0);
/* "spacy/en.pyx":78
* elif c == u'\n':
* return True
* elif c == u'\t': # <<<<<<<<<<<<<<
* return True
* else:
*/
switch (__pyx_v_c) {
/* "spacy/en.pyx":74
* # TODO: Support other unicode spaces
* # https://www.cs.tut.fi/~jkorpela/chars/spaces.html
* if c == u' ': # <<<<<<<<<<<<<<
* return True
* elif c == u'\n':
*/
case 32:
/* "spacy/en.pyx":75
* # https://www.cs.tut.fi/~jkorpela/chars/spaces.html
* if c == u' ':
* return True # <<<<<<<<<<<<<<
* elif c == u'\n':
* return True
*/
__pyx_r = 1;
goto __pyx_L0;
break;
/* "spacy/en.pyx":76
* if c == u' ':
* return True
* elif c == u'\n': # <<<<<<<<<<<<<<
* return True
* elif c == u'\t':
*/
case 10:
/* "spacy/en.pyx":77
* return True
* elif c == u'\n':
* return True # <<<<<<<<<<<<<<
* elif c == u'\t':
* return True
*/
__pyx_r = 1;
goto __pyx_L0;
break;
/* "spacy/en.pyx":78
* elif c == u'\n':
* return True
* elif c == u'\t': # <<<<<<<<<<<<<<
* return True
* else:
*/
case 9:
/* "spacy/en.pyx":79
* return True
* elif c == u'\t':
* return True # <<<<<<<<<<<<<<
* else:
* return False
*/
__pyx_r = 1;
goto __pyx_L0;
break;
default:
/* "spacy/en.pyx":81
* return True
* else:
* return False # <<<<<<<<<<<<<<
*
* cpdef Lexeme_addr lookup(unicode string) except 0:
*/
__pyx_r = 0;
goto __pyx_L0;
break;
}
/* "spacy/en.pyx":71
* return tokens
*
* cdef inline bint is_whitespace(Py_UNICODE c): # <<<<<<<<<<<<<<
* # TODO: Support other unicode spaces
* # https://www.cs.tut.fi/~jkorpela/chars/spaces.html
*/
/* function exit code */
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* "spacy/en.pyx":83
* return False
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cpdef Lexeme_addr lookup(unicode string) except 0: # <<<<<<<<<<<<<<
* '''.. function:: enumerate(sequence[, start=0])
* Fetch a Lexeme representing a word string. If the word has not been seen,
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pw_5spacy_2en_5lookup(PyObject *__pyx_self, PyObject *__pyx_v_string); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static __pyx_t_5spacy_2en_Lexeme_addr __pyx_f_5spacy_2en_lookup(PyObject *__pyx_v_string, CYTHON_UNUSED int __pyx_skip_dispatch) {
size_t __pyx_v_length;
__pyx_t_5spacy_6lexeme_StringHash __pyx_v_hashed;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_v_word_ptr;
__pyx_t_5spacy_2en_Lexeme_addr __pyx_r;
__Pyx_RefNannyDeclarations
int __pyx_t_1;
int __pyx_t_2;
Py_ssize_t __pyx_t_3;
__pyx_t_5spacy_6lexeme_StringHash __pyx_t_4;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_t_5;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("lookup", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":91
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* To specify the boundaries of the word if it has not been seen, use lookup_chunk.
* '''
* if string == '': # <<<<<<<<<<<<<<
* return <Lexeme_addr>&BLANK_WORD
* cdef size_t length = len(string)
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = (__Pyx_PyUnicode_Equals(__pyx_v_string, __pyx_kp_u_, Py_EQ)); if (unlikely(__pyx_t_1 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 91; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_t_2 = (__pyx_t_1 != 0);
if (__pyx_t_2) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":92
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* '''
* if string == '':
* return <Lexeme_addr>&BLANK_WORD # <<<<<<<<<<<<<<
* cdef size_t length = len(string)
* cdef StringHash hashed = hash_string(string, length)
*/
__pyx_r = ((__pyx_t_5spacy_2en_Lexeme_addr)(&__pyx_v_5spacy_2en_BLANK_WORD));
goto __pyx_L0;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":93
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if string == '':
* return <Lexeme_addr>&BLANK_WORD
* cdef size_t length = len(string) # <<<<<<<<<<<<<<
* cdef StringHash hashed = hash_string(string, length)
* cdef Lexeme* word_ptr = LEXEMES[hashed]
*/
if (unlikely(__pyx_v_string == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 93; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_3 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_string); if (unlikely(__pyx_t_3 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 93; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_length = __pyx_t_3;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":94
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* return <Lexeme_addr>&BLANK_WORD
* cdef size_t length = len(string)
* cdef StringHash hashed = hash_string(string, length) # <<<<<<<<<<<<<<
* cdef Lexeme* word_ptr = LEXEMES[hashed]
* cdef size_t n
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = __pyx_f_5spacy_2en_hash_string(__pyx_v_string, __pyx_v_length); if (unlikely(__pyx_t_4 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 94; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_hashed = __pyx_t_4;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":95
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef size_t length = len(string)
* cdef StringHash hashed = hash_string(string, length)
* cdef Lexeme* word_ptr = LEXEMES[hashed] # <<<<<<<<<<<<<<
* cdef size_t n
* if word_ptr == NULL:
*/
__pyx_v_word_ptr = (__pyx_v_5spacy_2en_LEXEMES[__pyx_v_hashed]);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":97
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef Lexeme* word_ptr = LEXEMES[hashed]
* cdef size_t n
* if word_ptr == NULL: # <<<<<<<<<<<<<<
* word_ptr = _add(hashed, string, _find_split(string, length), length)
* return <Lexeme_addr>word_ptr
*/
__pyx_t_2 = ((__pyx_v_word_ptr == NULL) != 0);
if (__pyx_t_2) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":98
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef size_t n
* if word_ptr == NULL:
* word_ptr = _add(hashed, string, _find_split(string, length), length) # <<<<<<<<<<<<<<
* return <Lexeme_addr>word_ptr
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_5 = __pyx_f_5spacy_2en__add(__pyx_v_hashed, __pyx_v_string, __pyx_f_5spacy_2en__find_split(__pyx_v_string, __pyx_v_length), __pyx_v_length); if (unlikely(__pyx_t_5 == NULL)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 98; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_word_ptr = __pyx_t_5;
goto __pyx_L4;
}
__pyx_L4:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":99
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if word_ptr == NULL:
* word_ptr = _add(hashed, string, _find_split(string, length), length)
* return <Lexeme_addr>word_ptr # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = ((__pyx_t_5spacy_2en_Lexeme_addr)__pyx_v_word_ptr);
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":83
* return False
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* cpdef Lexeme_addr lookup(unicode string) except 0: # <<<<<<<<<<<<<<
* '''.. function:: enumerate(sequence[, start=0])
* Fetch a Lexeme representing a word string. If the word has not been seen,
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_AddTraceback("spacy.en.lookup", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = 0;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pw_5spacy_2en_5lookup(PyObject *__pyx_self, PyObject *__pyx_v_string); /*proto*/
static char __pyx_doc_5spacy_2en_4lookup[] = ".. function:: enumerate(sequence[, start=0])\n Fetch a Lexeme representing a word string. If the word has not been seen,\n construct one, splitting off any attached punctuation or clitics. A\n reference to BLANK_WORD is returned for the empty string.\n \n To specify the boundaries of the word if it has not been seen, use lookup_chunk.\n ";
static PyObject *__pyx_pw_5spacy_2en_5lookup(PyObject *__pyx_self, PyObject *__pyx_v_string) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
CYTHON_UNUSED int __pyx_lineno = 0;
CYTHON_UNUSED const char *__pyx_filename = NULL;
CYTHON_UNUSED int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("lookup (wrapper)", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_string), (&PyUnicode_Type), 1, "string", 1))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 83; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_r = __pyx_pf_5spacy_2en_4lookup(__pyx_self, ((PyObject*)__pyx_v_string));
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/* function exit code */
goto __pyx_L0;
__pyx_L1_error:;
__pyx_r = NULL;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pf_5spacy_2en_4lookup(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_string) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
__pyx_t_5spacy_2en_Lexeme_addr __pyx_t_1;
PyObject *__pyx_t_2 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("lookup", 0);
__Pyx_XDECREF(__pyx_r);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __pyx_f_5spacy_2en_lookup(__pyx_v_string, 0); if (unlikely(__pyx_t_1 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 83; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_2 = __Pyx_PyInt_FromSize_t(__pyx_t_1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 83; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
__pyx_r = __pyx_t_2;
__pyx_t_2 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_2);
__Pyx_AddTraceback("spacy.en.lookup", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":102
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef Lexeme_addr lookup_chunk(unicode string, int start, int end) except 0: # <<<<<<<<<<<<<<
* '''Fetch a Lexeme representing a word string. If the word has not been seen,
* construct one, given the specified start and end indices. A negative index
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pw_5spacy_2en_7lookup_chunk(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static __pyx_t_5spacy_2en_Lexeme_addr __pyx_f_5spacy_2en_lookup_chunk(PyObject *__pyx_v_string, int __pyx_v_start, CYTHON_UNUSED int __pyx_v_end, CYTHON_UNUSED int __pyx_skip_dispatch) {
size_t __pyx_v_length;
__pyx_t_5spacy_6lexeme_StringHash __pyx_v_hashed;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_v_chunk_ptr;
__pyx_t_5spacy_2en_Lexeme_addr __pyx_r;
__Pyx_RefNannyDeclarations
int __pyx_t_1;
int __pyx_t_2;
Py_ssize_t __pyx_t_3;
__pyx_t_5spacy_6lexeme_StringHash __pyx_t_4;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_t_5;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("lookup_chunk", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":110
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* A reference to BLANK_WORD is returned for the empty string.
* '''
* if string == '': # <<<<<<<<<<<<<<
* return <Lexeme_addr>&BLANK_WORD
* cdef size_t length = len(string)
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = (__Pyx_PyUnicode_Equals(__pyx_v_string, __pyx_kp_u_, Py_EQ)); if (unlikely(__pyx_t_1 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 110; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_t_2 = (__pyx_t_1 != 0);
if (__pyx_t_2) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":111
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* '''
* if string == '':
* return <Lexeme_addr>&BLANK_WORD # <<<<<<<<<<<<<<
* cdef size_t length = len(string)
* cdef StringHash hashed = hash_string(string, length)
*/
__pyx_r = ((__pyx_t_5spacy_2en_Lexeme_addr)(&__pyx_v_5spacy_2en_BLANK_WORD));
goto __pyx_L0;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":112
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if string == '':
* return <Lexeme_addr>&BLANK_WORD
* cdef size_t length = len(string) # <<<<<<<<<<<<<<
* cdef StringHash hashed = hash_string(string, length)
* cdef Lexeme* chunk_ptr = LEXEMES[hashed]
*/
if (unlikely(__pyx_v_string == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 112; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_3 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_string); if (unlikely(__pyx_t_3 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 112; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_length = __pyx_t_3;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":113
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* return <Lexeme_addr>&BLANK_WORD
* cdef size_t length = len(string)
* cdef StringHash hashed = hash_string(string, length) # <<<<<<<<<<<<<<
* cdef Lexeme* chunk_ptr = LEXEMES[hashed]
* if chunk_ptr == NULL:
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = __pyx_f_5spacy_2en_hash_string(__pyx_v_string, __pyx_v_length); if (unlikely(__pyx_t_4 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 113; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_hashed = __pyx_t_4;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":114
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef size_t length = len(string)
* cdef StringHash hashed = hash_string(string, length)
* cdef Lexeme* chunk_ptr = LEXEMES[hashed] # <<<<<<<<<<<<<<
* if chunk_ptr == NULL:
* chunk_ptr = _add(hashed, string, start, length)
*/
__pyx_v_chunk_ptr = (__pyx_v_5spacy_2en_LEXEMES[__pyx_v_hashed]);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":115
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef StringHash hashed = hash_string(string, length)
* cdef Lexeme* chunk_ptr = LEXEMES[hashed]
* if chunk_ptr == NULL: # <<<<<<<<<<<<<<
* chunk_ptr = _add(hashed, string, start, length)
* return <Lexeme_addr>chunk_ptr
*/
__pyx_t_2 = ((__pyx_v_chunk_ptr == NULL) != 0);
if (__pyx_t_2) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":116
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef Lexeme* chunk_ptr = LEXEMES[hashed]
* if chunk_ptr == NULL:
* chunk_ptr = _add(hashed, string, start, length) # <<<<<<<<<<<<<<
* return <Lexeme_addr>chunk_ptr
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_5 = __pyx_f_5spacy_2en__add(__pyx_v_hashed, __pyx_v_string, __pyx_v_start, __pyx_v_length); if (unlikely(__pyx_t_5 == NULL)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 116; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_chunk_ptr = __pyx_t_5;
goto __pyx_L4;
}
__pyx_L4:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":117
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if chunk_ptr == NULL:
* chunk_ptr = _add(hashed, string, start, length)
* return <Lexeme_addr>chunk_ptr # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = ((__pyx_t_5spacy_2en_Lexeme_addr)__pyx_v_chunk_ptr);
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":102
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef Lexeme_addr lookup_chunk(unicode string, int start, int end) except 0: # <<<<<<<<<<<<<<
* '''Fetch a Lexeme representing a word string. If the word has not been seen,
* construct one, given the specified start and end indices. A negative index
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_AddTraceback("spacy.en.lookup_chunk", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = 0;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pw_5spacy_2en_7lookup_chunk(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/
static char __pyx_doc_5spacy_2en_6lookup_chunk[] = "Fetch a Lexeme representing a word string. If the word has not been seen,\n construct one, given the specified start and end indices. A negative index\n significes 0 for start, and the string length for end --- i.e. the string\n will not be sliced if start == -1 and end == -1.\n \n A reference to BLANK_WORD is returned for the empty string.\n ";
static PyObject *__pyx_pw_5spacy_2en_7lookup_chunk(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
PyObject *__pyx_v_string = 0;
int __pyx_v_start;
int __pyx_v_end;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("lookup_chunk (wrapper)", 0);
{
static PyObject **__pyx_pyargnames[] = {&__pyx_n_s_string,&__pyx_n_s_start,&__pyx_n_s_end,0};
PyObject* values[3] = {0,0,0};
if (unlikely(__pyx_kwds)) {
Py_ssize_t kw_args;
const Py_ssize_t pos_args = PyTuple_GET_SIZE(__pyx_args);
switch (pos_args) {
case 3: values[2] = PyTuple_GET_ITEM(__pyx_args, 2);
case 2: values[1] = PyTuple_GET_ITEM(__pyx_args, 1);
case 1: values[0] = PyTuple_GET_ITEM(__pyx_args, 0);
case 0: break;
default: goto __pyx_L5_argtuple_error;
}
kw_args = PyDict_Size(__pyx_kwds);
switch (pos_args) {
case 0:
if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_string)) != 0)) kw_args--;
else goto __pyx_L5_argtuple_error;
case 1:
if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_start)) != 0)) kw_args--;
else {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__Pyx_RaiseArgtupleInvalid("lookup_chunk", 1, 3, 3, 1); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
case 2:
if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_end)) != 0)) kw_args--;
else {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__Pyx_RaiseArgtupleInvalid("lookup_chunk", 1, 3, 3, 2); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
if (unlikely(kw_args > 0)) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "lookup_chunk") < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
} else if (PyTuple_GET_SIZE(__pyx_args) != 3) {
goto __pyx_L5_argtuple_error;
} else {
values[0] = PyTuple_GET_ITEM(__pyx_args, 0);
values[1] = PyTuple_GET_ITEM(__pyx_args, 1);
values[2] = PyTuple_GET_ITEM(__pyx_args, 2);
}
__pyx_v_string = ((PyObject*)values[0]);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_v_start = __Pyx_PyInt_As_int(values[1]); if (unlikely((__pyx_v_start == (int)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
__pyx_v_end = __Pyx_PyInt_As_int(values[2]); if (unlikely((__pyx_v_end == (int)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L5_argtuple_error:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__Pyx_RaiseArgtupleInvalid("lookup_chunk", 1, 3, 3, PyTuple_GET_SIZE(__pyx_args)); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.en.lookup_chunk", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_string), (&PyUnicode_Type), 1, "string", 1))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_r = __pyx_pf_5spacy_2en_6lookup_chunk(__pyx_self, __pyx_v_string, __pyx_v_start, __pyx_v_end);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/* function exit code */
goto __pyx_L0;
__pyx_L1_error:;
__pyx_r = NULL;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pf_5spacy_2en_6lookup_chunk(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_string, int __pyx_v_start, int __pyx_v_end) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
__pyx_t_5spacy_2en_Lexeme_addr __pyx_t_1;
PyObject *__pyx_t_2 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("lookup_chunk", 0);
__Pyx_XDECREF(__pyx_r);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __pyx_f_5spacy_2en_lookup_chunk(__pyx_v_string, __pyx_v_start, __pyx_v_end, 0); if (unlikely(__pyx_t_1 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_2 = __Pyx_PyInt_FromSize_t(__pyx_t_1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 102; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
__pyx_r = __pyx_t_2;
__pyx_t_2 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_2);
__Pyx_AddTraceback("spacy.en.lookup_chunk", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":120
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef StringHash hash_string(unicode s, size_t length) except 0: # <<<<<<<<<<<<<<
* '''Hash unicode with MurmurHash64A'''
* assert length
*/
static __pyx_t_5spacy_6lexeme_StringHash __pyx_f_5spacy_2en_hash_string(PyObject *__pyx_v_s, size_t __pyx_v_length) {
__pyx_t_5spacy_6lexeme_StringHash __pyx_r;
__Pyx_RefNannyDeclarations
__pyx_t_5spacy_2en_string_ptr __pyx_t_1;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("hash_string", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":122
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef StringHash hash_string(unicode s, size_t length) except 0:
* '''Hash unicode with MurmurHash64A'''
* assert length # <<<<<<<<<<<<<<
* return MurmurHash64A(<string_ptr>s, length * sizeof(Py_UNICODE), 0)
*
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
if (unlikely(!(__pyx_v_length != 0))) {
PyErr_SetNone(PyExc_AssertionError);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 122; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
#endif
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":123
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* '''Hash unicode with MurmurHash64A'''
* assert length
* return MurmurHash64A(<string_ptr>s, length * sizeof(Py_UNICODE), 0) # <<<<<<<<<<<<<<
*
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_PyUnicode_AsUnicode(__pyx_v_s); if (unlikely((!__pyx_t_1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 123; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_r = MurmurHash64A(((__pyx_t_5spacy_2en_string_ptr)__pyx_t_1), (__pyx_v_length * (sizeof(Py_UNICODE))), 0);
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":120
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef StringHash hash_string(unicode s, size_t length) except 0: # <<<<<<<<<<<<<<
* '''Hash unicode with MurmurHash64A'''
* assert length
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_AddTraceback("spacy.en.hash_string", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = 0;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":126
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef unicode unhash(StringHash hash_value): # <<<<<<<<<<<<<<
* '''Fetch a string from the reverse index, given its hash value.'''
* cdef string_ptr string = STRINGS[hash_value]
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pw_5spacy_2en_9unhash(PyObject *__pyx_self, PyObject *__pyx_arg_hash_value); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_f_5spacy_2en_unhash(__pyx_t_5spacy_6lexeme_StringHash __pyx_v_hash_value, CYTHON_UNUSED int __pyx_skip_dispatch) {
__pyx_t_5spacy_2en_string_ptr __pyx_v_string;
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
PyObject *__pyx_t_1 = NULL;
PyObject *__pyx_t_2 = NULL;
__pyx_t_5spacy_2en_string_ptr __pyx_t_3;
int __pyx_t_4;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("unhash", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":128
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cpdef unicode unhash(StringHash hash_value):
* '''Fetch a string from the reverse index, given its hash value.'''
* cdef string_ptr string = STRINGS[hash_value] # <<<<<<<<<<<<<<
* if string == NULL:
* raise ValueError(hash_value)
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_STRINGS); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 128; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __Pyx_GetItemInt(__pyx_t_1, __pyx_v_hash_value, __pyx_t_5spacy_6lexeme_StringHash, 0, __Pyx_PyInt_From_uint64_t, 0, 0, 1); if (unlikely(__pyx_t_2 == NULL)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 128; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_3 = __Pyx_PyUnicode_AsUnicode(__pyx_t_2); if (unlikely((!__pyx_t_3) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 128; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
__pyx_v_string = __pyx_t_3;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":129
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* '''Fetch a string from the reverse index, given its hash value.'''
* cdef string_ptr string = STRINGS[hash_value]
* if string == NULL: # <<<<<<<<<<<<<<
* raise ValueError(hash_value)
*
*/
__pyx_t_4 = ((__pyx_v_string == NULL) != 0);
if (__pyx_t_4) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":130
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef string_ptr string = STRINGS[hash_value]
* if string == NULL:
* raise ValueError(hash_value) # <<<<<<<<<<<<<<
*
* return string
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __Pyx_PyInt_From_uint64_t(__pyx_v_hash_value); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 130; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 130; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_t_2);
__Pyx_GIVEREF(__pyx_t_2);
__pyx_t_2 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_1, NULL); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 130; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
__Pyx_Raise(__pyx_t_2, 0, 0, 0);
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 130; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":132
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* raise ValueError(hash_value)
*
* return string # <<<<<<<<<<<<<<
*
*
*/
__Pyx_XDECREF(__pyx_r);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __Pyx_PyUnicode_FromUnicode(__pyx_v_string); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 132; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (!(likely(PyUnicode_CheckExact(__pyx_t_2))||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "unicode", Py_TYPE(__pyx_t_2)->tp_name), 0))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 132; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_r = ((PyObject*)__pyx_t_2);
__pyx_t_2 = 0;
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":126
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef unicode unhash(StringHash hash_value): # <<<<<<<<<<<<<<
* '''Fetch a string from the reverse index, given its hash value.'''
* cdef string_ptr string = STRINGS[hash_value]
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_XDECREF(__pyx_t_2);
__Pyx_AddTraceback("spacy.en.unhash", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = 0;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pw_5spacy_2en_9unhash(PyObject *__pyx_self, PyObject *__pyx_arg_hash_value); /*proto*/
static char __pyx_doc_5spacy_2en_8unhash[] = "Fetch a string from the reverse index, given its hash value.";
static PyObject *__pyx_pw_5spacy_2en_9unhash(PyObject *__pyx_self, PyObject *__pyx_arg_hash_value) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_t_5spacy_6lexeme_StringHash __pyx_v_hash_value;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("unhash (wrapper)", 0);
assert(__pyx_arg_hash_value); {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_v_hash_value = __Pyx_PyInt_As_uint64_t(__pyx_arg_hash_value); if (unlikely((__pyx_v_hash_value == (uint64_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 126; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.en.unhash", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_r = __pyx_pf_5spacy_2en_8unhash(__pyx_self, ((__pyx_t_5spacy_6lexeme_StringHash)__pyx_v_hash_value));
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pf_5spacy_2en_8unhash(CYTHON_UNUSED PyObject *__pyx_self, __pyx_t_5spacy_6lexeme_StringHash __pyx_v_hash_value) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
PyObject *__pyx_t_1 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("unhash", 0);
__Pyx_XDECREF(__pyx_r);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __pyx_f_5spacy_2en_unhash(__pyx_v_hash_value, 0); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 126; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_AddTraceback("spacy.en.unhash", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":135
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef unicode normalize_word_string(unicode word): # <<<<<<<<<<<<<<
* '''Return a normalized version of the word, mapping:
* - 4 digit strings into !YEAR
*/
static PyObject *__pyx_f_5spacy_2en_normalize_word_string(PyObject *__pyx_v_word) {
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
PyObject *__pyx_t_1 = NULL;
PyObject *__pyx_t_2 = NULL;
int __pyx_t_3;
Py_ssize_t __pyx_t_4;
int __pyx_t_5;
int __pyx_t_6;
Py_UCS4 __pyx_t_7;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("normalize_word_string", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":142
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* '''
* cdef unicode s
* if word.isdigit() and len(word) == 4: # <<<<<<<<<<<<<<
* return '!YEAR'
* elif word[0].isdigit():
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_isdigit); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 142; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_empty_tuple, NULL); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 142; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_3 = __Pyx_PyObject_IsTrue(__pyx_t_2); if (unlikely(__pyx_t_3 < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 142; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
if (__pyx_t_3) {
if (unlikely(__pyx_v_word == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 142; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_word); if (unlikely(__pyx_t_4 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 142; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_t_5 = (__pyx_t_4 == 4);
__pyx_t_6 = __pyx_t_5;
} else {
__pyx_t_6 = __pyx_t_3;
}
if (__pyx_t_6) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":143
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef unicode s
* if word.isdigit() and len(word) == 4:
* return '!YEAR' # <<<<<<<<<<<<<<
* elif word[0].isdigit():
* return '!DIGITS'
*/
__Pyx_XDECREF(__pyx_r);
__Pyx_INCREF(__pyx_kp_u_YEAR);
__pyx_r = __pyx_kp_u_YEAR;
goto __pyx_L0;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":144
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if word.isdigit() and len(word) == 4:
* return '!YEAR'
* elif word[0].isdigit(): # <<<<<<<<<<<<<<
* return '!DIGITS'
* else:
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_7 = __Pyx_GetItemInt_Unicode(__pyx_v_word, 0, long, 1, __Pyx_PyInt_From_long, 0, 0, 1); if (unlikely(__pyx_t_7 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 144; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_t_6 = Py_UNICODE_ISDIGIT(__pyx_t_7);
if ((__pyx_t_6 != 0)) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":145
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* return '!YEAR'
* elif word[0].isdigit():
* return '!DIGITS' # <<<<<<<<<<<<<<
* else:
* return word.lower()
*/
__Pyx_XDECREF(__pyx_r);
__Pyx_INCREF(__pyx_kp_u_DIGITS);
__pyx_r = __pyx_kp_u_DIGITS;
goto __pyx_L0;
}
/*else*/ {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":147
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* return '!DIGITS'
* else:
* return word.lower() # <<<<<<<<<<<<<<
*
*
*/
__Pyx_XDECREF(__pyx_r);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_lower); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 147; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_empty_tuple, NULL); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 147; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (!(likely(PyUnicode_CheckExact(__pyx_t_1))||((__pyx_t_1) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "unicode", Py_TYPE(__pyx_t_1)->tp_name), 0))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 147; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_r = ((PyObject*)__pyx_t_1);
__pyx_t_1 = 0;
goto __pyx_L0;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":135
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef unicode normalize_word_string(unicode word): # <<<<<<<<<<<<<<
* '''Return a normalized version of the word, mapping:
* - 4 digit strings into !YEAR
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_XDECREF(__pyx_t_2);
__Pyx_AddTraceback("spacy.en.normalize_word_string", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = 0;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":150
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef unicode _substr(unicode string, int start, int end, size_t length): # <<<<<<<<<<<<<<
* if end >= length:
* end = -1
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pw_5spacy_2en_11_substr(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_f_5spacy_2en__substr(PyObject *__pyx_v_string, int __pyx_v_start, int __pyx_v_end, size_t __pyx_v_length, CYTHON_UNUSED int __pyx_skip_dispatch) {
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
int __pyx_t_1;
int __pyx_t_2;
int __pyx_t_3;
PyObject *__pyx_t_4 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("_substr", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":151
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* cpdef unicode _substr(unicode string, int start, int end, size_t length):
* if end >= length: # <<<<<<<<<<<<<<
* end = -1
* if start >= length:
*/
__pyx_t_1 = ((__pyx_v_end >= __pyx_v_length) != 0);
if (__pyx_t_1) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":152
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cpdef unicode _substr(unicode string, int start, int end, size_t length):
* if end >= length:
* end = -1 # <<<<<<<<<<<<<<
* if start >= length:
* start = 0
*/
__pyx_v_end = -1;
goto __pyx_L3;
}
__pyx_L3:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":153
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if end >= length:
* end = -1
* if start >= length: # <<<<<<<<<<<<<<
* start = 0
* if start <= 0 and end < 0:
*/
__pyx_t_1 = ((__pyx_v_start >= __pyx_v_length) != 0);
if (__pyx_t_1) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":154
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* end = -1
* if start >= length:
* start = 0 # <<<<<<<<<<<<<<
* if start <= 0 and end < 0:
* return string
*/
__pyx_v_start = 0;
goto __pyx_L4;
}
__pyx_L4:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":155
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if start >= length:
* start = 0
* if start <= 0 and end < 0: # <<<<<<<<<<<<<<
* return string
* elif start < 0:
*/
__pyx_t_1 = ((__pyx_v_start <= 0) != 0);
if (__pyx_t_1) {
__pyx_t_2 = ((__pyx_v_end < 0) != 0);
__pyx_t_3 = __pyx_t_2;
} else {
__pyx_t_3 = __pyx_t_1;
}
if (__pyx_t_3) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":156
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* start = 0
* if start <= 0 and end < 0:
* return string # <<<<<<<<<<<<<<
* elif start < 0:
* start = 0
*/
__Pyx_XDECREF(__pyx_r);
__Pyx_INCREF(__pyx_v_string);
__pyx_r = __pyx_v_string;
goto __pyx_L0;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":157
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if start <= 0 and end < 0:
* return string
* elif start < 0: # <<<<<<<<<<<<<<
* start = 0
* elif end < 0:
*/
__pyx_t_3 = ((__pyx_v_start < 0) != 0);
if (__pyx_t_3) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":158
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* return string
* elif start < 0:
* start = 0 # <<<<<<<<<<<<<<
* elif end < 0:
* end = length
*/
__pyx_v_start = 0;
goto __pyx_L5;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":159
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* elif start < 0:
* start = 0
* elif end < 0: # <<<<<<<<<<<<<<
* end = length
* return string[start:end]
*/
__pyx_t_3 = ((__pyx_v_end < 0) != 0);
if (__pyx_t_3) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":160
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* start = 0
* elif end < 0:
* end = length # <<<<<<<<<<<<<<
* return string[start:end]
*
*/
__pyx_v_end = __pyx_v_length;
goto __pyx_L5;
}
__pyx_L5:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":161
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* elif end < 0:
* end = length
* return string[start:end] # <<<<<<<<<<<<<<
*
*
*/
__Pyx_XDECREF(__pyx_r);
if (unlikely(__pyx_v_string == Py_None)) {
PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 161; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = __Pyx_PyUnicode_Substring(__pyx_v_string, __pyx_v_start, __pyx_v_end); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 161; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_4);
__pyx_r = ((PyObject*)__pyx_t_4);
__pyx_t_4 = 0;
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":150
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef unicode _substr(unicode string, int start, int end, size_t length): # <<<<<<<<<<<<<<
* if end >= length:
* end = -1
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_4);
__Pyx_AddTraceback("spacy.en._substr", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = 0;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pw_5spacy_2en_11_substr(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/
static PyObject *__pyx_pw_5spacy_2en_11_substr(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
PyObject *__pyx_v_string = 0;
int __pyx_v_start;
int __pyx_v_end;
size_t __pyx_v_length;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("_substr (wrapper)", 0);
{
static PyObject **__pyx_pyargnames[] = {&__pyx_n_s_string,&__pyx_n_s_start,&__pyx_n_s_end,&__pyx_n_s_length,0};
PyObject* values[4] = {0,0,0,0};
if (unlikely(__pyx_kwds)) {
Py_ssize_t kw_args;
const Py_ssize_t pos_args = PyTuple_GET_SIZE(__pyx_args);
switch (pos_args) {
case 4: values[3] = PyTuple_GET_ITEM(__pyx_args, 3);
case 3: values[2] = PyTuple_GET_ITEM(__pyx_args, 2);
case 2: values[1] = PyTuple_GET_ITEM(__pyx_args, 1);
case 1: values[0] = PyTuple_GET_ITEM(__pyx_args, 0);
case 0: break;
default: goto __pyx_L5_argtuple_error;
}
kw_args = PyDict_Size(__pyx_kwds);
switch (pos_args) {
case 0:
if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_string)) != 0)) kw_args--;
else goto __pyx_L5_argtuple_error;
case 1:
if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_start)) != 0)) kw_args--;
else {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__Pyx_RaiseArgtupleInvalid("_substr", 1, 4, 4, 1); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
case 2:
if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_end)) != 0)) kw_args--;
else {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__Pyx_RaiseArgtupleInvalid("_substr", 1, 4, 4, 2); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
case 3:
if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_length)) != 0)) kw_args--;
else {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__Pyx_RaiseArgtupleInvalid("_substr", 1, 4, 4, 3); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
if (unlikely(kw_args > 0)) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "_substr") < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
} else if (PyTuple_GET_SIZE(__pyx_args) != 4) {
goto __pyx_L5_argtuple_error;
} else {
values[0] = PyTuple_GET_ITEM(__pyx_args, 0);
values[1] = PyTuple_GET_ITEM(__pyx_args, 1);
values[2] = PyTuple_GET_ITEM(__pyx_args, 2);
values[3] = PyTuple_GET_ITEM(__pyx_args, 3);
}
__pyx_v_string = ((PyObject*)values[0]);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_v_start = __Pyx_PyInt_As_int(values[1]); if (unlikely((__pyx_v_start == (int)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
__pyx_v_end = __Pyx_PyInt_As_int(values[2]); if (unlikely((__pyx_v_end == (int)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
__pyx_v_length = __Pyx_PyInt_As_size_t(values[3]); if (unlikely((__pyx_v_length == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L5_argtuple_error:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__Pyx_RaiseArgtupleInvalid("_substr", 1, 4, 4, PyTuple_GET_SIZE(__pyx_args)); {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.en._substr", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_string), (&PyUnicode_Type), 1, "string", 1))) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_r = __pyx_pf_5spacy_2en_10_substr(__pyx_self, __pyx_v_string, __pyx_v_start, __pyx_v_end, __pyx_v_length);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/* function exit code */
goto __pyx_L0;
__pyx_L1_error:;
__pyx_r = NULL;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static PyObject *__pyx_pf_5spacy_2en_10_substr(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_string, int __pyx_v_start, int __pyx_v_end, size_t __pyx_v_length) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
PyObject *__pyx_t_1 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("_substr", 0);
__Pyx_XDECREF(__pyx_r);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __pyx_f_5spacy_2en__substr(__pyx_v_string, __pyx_v_start, __pyx_v_end, __pyx_v_length, 0); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 150; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_AddTraceback("spacy.en._substr", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":164
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef Lexeme* _add(StringHash hashed, unicode string, int split, size_t length) except NULL: # <<<<<<<<<<<<<<
* assert string
* assert split <= length
*/
static struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_f_5spacy_2en__add(__pyx_t_5spacy_6lexeme_StringHash __pyx_v_hashed, PyObject *__pyx_v_string, int __pyx_v_split, size_t __pyx_v_length) {
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_v_word;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_r;
__Pyx_RefNannyDeclarations
int __pyx_t_1;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_t_2;
PyObject *__pyx_t_3 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("_add", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":165
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* cdef Lexeme* _add(StringHash hashed, unicode string, int split, size_t length) except NULL:
* assert string # <<<<<<<<<<<<<<
* assert split <= length
* word = _init_lexeme(string, hashed, split, length)
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
__pyx_t_1 = (__pyx_v_string != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_string) != 0);
if (unlikely(!__pyx_t_1)) {
PyErr_SetNone(PyExc_AssertionError);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 165; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
#endif
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":166
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef Lexeme* _add(StringHash hashed, unicode string, int split, size_t length) except NULL:
* assert string
* assert split <= length # <<<<<<<<<<<<<<
* word = _init_lexeme(string, hashed, split, length)
* LEXEMES[hashed] = word
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
if (unlikely(!((__pyx_v_split <= __pyx_v_length) != 0))) {
PyErr_SetNone(PyExc_AssertionError);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 166; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
#endif
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":167
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* assert string
* assert split <= length
* word = _init_lexeme(string, hashed, split, length) # <<<<<<<<<<<<<<
* LEXEMES[hashed] = word
* STRINGS[hashed] = string
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __pyx_f_5spacy_2en__init_lexeme(__pyx_v_string, __pyx_v_hashed, __pyx_v_split, __pyx_v_length); if (unlikely(__pyx_t_2 == NULL)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 167; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_word = __pyx_t_2;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":168
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* assert split <= length
* word = _init_lexeme(string, hashed, split, length)
* LEXEMES[hashed] = word # <<<<<<<<<<<<<<
* STRINGS[hashed] = string
* return word
*/
(__pyx_v_5spacy_2en_LEXEMES[__pyx_v_hashed]) = __pyx_v_word;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":169
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* word = _init_lexeme(string, hashed, split, length)
* LEXEMES[hashed] = word
* STRINGS[hashed] = string # <<<<<<<<<<<<<<
* return word
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_STRINGS); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 169; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_3);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(__Pyx_SetItemInt(__pyx_t_3, __pyx_v_hashed, __pyx_v_string, __pyx_t_5spacy_6lexeme_StringHash, 0, __Pyx_PyInt_From_uint64_t, 0, 0, 1) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 169; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":170
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* LEXEMES[hashed] = word
* STRINGS[hashed] = string
* return word # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = __pyx_v_word;
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":164
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef Lexeme* _add(StringHash hashed, unicode string, int split, size_t length) except NULL: # <<<<<<<<<<<<<<
* assert string
* assert split <= length
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_3);
__Pyx_AddTraceback("spacy.en._add", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":173
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef Lexeme* _init_lexeme(unicode string, StringHash hashed, # <<<<<<<<<<<<<<
* int split, size_t length) except NULL:
* assert split <= length
*/
static struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_f_5spacy_2en__init_lexeme(PyObject *__pyx_v_string, __pyx_t_5spacy_6lexeme_StringHash __pyx_v_hashed, int __pyx_v_split, size_t __pyx_v_length) {
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_v_word;
PyObject *__pyx_v_tail_string = 0;
PyObject *__pyx_v_lex = 0;
PyObject *__pyx_v_normed = 0;
PyObject *__pyx_v_last3 = 0;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_r;
__Pyx_RefNannyDeclarations
long __pyx_t_1;
int __pyx_t_2;
Py_UCS4 __pyx_t_3;
int __pyx_t_4;
int __pyx_t_5;
PyObject *__pyx_t_6 = NULL;
Py_ssize_t __pyx_t_7;
__pyx_t_5spacy_6lexeme_StringHash __pyx_t_8;
__pyx_t_5spacy_2en_Lexeme_addr __pyx_t_9;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("_init_lexeme", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":175
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef Lexeme* _init_lexeme(unicode string, StringHash hashed,
* int split, size_t length) except NULL:
* assert split <= length # <<<<<<<<<<<<<<
* cdef Lexeme* word = <Lexeme*>calloc(1, sizeof(Lexeme))
*
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
if (unlikely(!((__pyx_v_split <= __pyx_v_length) != 0))) {
PyErr_SetNone(PyExc_AssertionError);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 175; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
#endif
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":176
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* int split, size_t length) except NULL:
* assert split <= length
* cdef Lexeme* word = <Lexeme*>calloc(1, sizeof(Lexeme)) # <<<<<<<<<<<<<<
*
* word.first = <Py_UNICODE>(string[0] if string else 0)
*/
__pyx_v_word = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)calloc(1, (sizeof(struct __pyx_t_5spacy_6lexeme_Lexeme))));
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":178
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef Lexeme* word = <Lexeme*>calloc(1, sizeof(Lexeme))
*
* word.first = <Py_UNICODE>(string[0] if string else 0) # <<<<<<<<<<<<<<
* word.sic = hashed
*
*/
__pyx_t_2 = (__pyx_v_string != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_string) != 0);
if (__pyx_t_2) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_3 = __Pyx_GetItemInt_Unicode(__pyx_v_string, 0, long, 1, __Pyx_PyInt_From_long, 0, 0, 1); if (unlikely(__pyx_t_3 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 178; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_t_1 = __pyx_t_3;
} else {
__pyx_t_1 = 0;
}
__pyx_v_word->first = ((Py_UNICODE)__pyx_t_1);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":179
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* word.first = <Py_UNICODE>(string[0] if string else 0)
* word.sic = hashed # <<<<<<<<<<<<<<
*
* cdef unicode tail_string
*/
__pyx_v_word->sic = __pyx_v_hashed;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":183
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef unicode tail_string
* cdef unicode lex
* if split != 0 and split < length: # <<<<<<<<<<<<<<
* lex = _substr(string, 0, split, length)
* tail_string = _substr(string, split, length, length)
*/
__pyx_t_2 = ((__pyx_v_split != 0) != 0);
if (__pyx_t_2) {
__pyx_t_4 = ((__pyx_v_split < __pyx_v_length) != 0);
__pyx_t_5 = __pyx_t_4;
} else {
__pyx_t_5 = __pyx_t_2;
}
if (__pyx_t_5) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":184
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef unicode lex
* if split != 0 and split < length:
* lex = _substr(string, 0, split, length) # <<<<<<<<<<<<<<
* tail_string = _substr(string, split, length, length)
* else:
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = __pyx_f_5spacy_2en__substr(__pyx_v_string, 0, __pyx_v_split, __pyx_v_length, 0); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 184; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_6);
__pyx_v_lex = ((PyObject*)__pyx_t_6);
__pyx_t_6 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":185
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if split != 0 and split < length:
* lex = _substr(string, 0, split, length)
* tail_string = _substr(string, split, length, length) # <<<<<<<<<<<<<<
* else:
* lex = string
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = __pyx_f_5spacy_2en__substr(__pyx_v_string, __pyx_v_split, __pyx_v_length, __pyx_v_length, 0); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 185; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_6);
__pyx_v_tail_string = ((PyObject*)__pyx_t_6);
__pyx_t_6 = 0;
goto __pyx_L3;
}
/*else*/ {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":187
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* tail_string = _substr(string, split, length, length)
* else:
* lex = string # <<<<<<<<<<<<<<
* tail_string = ''
* assert lex
*/
__Pyx_INCREF(__pyx_v_string);
__pyx_v_lex = __pyx_v_string;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":188
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* else:
* lex = string
* tail_string = '' # <<<<<<<<<<<<<<
* assert lex
* cdef unicode normed = normalize_word_string(lex)
*/
__Pyx_INCREF(__pyx_kp_u_);
__pyx_v_tail_string = __pyx_kp_u_;
}
__pyx_L3:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":189
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* lex = string
* tail_string = ''
* assert lex # <<<<<<<<<<<<<<
* cdef unicode normed = normalize_word_string(lex)
* cdef unicode last3 = _substr(string, length - 3, length, length)
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
__pyx_t_5 = (__pyx_v_lex != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_lex) != 0);
if (unlikely(!__pyx_t_5)) {
PyErr_SetNone(PyExc_AssertionError);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 189; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
#endif
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":190
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* tail_string = ''
* assert lex
* cdef unicode normed = normalize_word_string(lex) # <<<<<<<<<<<<<<
* cdef unicode last3 = _substr(string, length - 3, length, length)
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = __pyx_f_5spacy_2en_normalize_word_string(__pyx_v_lex); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 190; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_6);
__pyx_v_normed = ((PyObject*)__pyx_t_6);
__pyx_t_6 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":191
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* assert lex
* cdef unicode normed = normalize_word_string(lex)
* cdef unicode last3 = _substr(string, length - 3, length, length) # <<<<<<<<<<<<<<
*
* assert normed
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = __pyx_f_5spacy_2en__substr(__pyx_v_string, (__pyx_v_length - 3), __pyx_v_length, __pyx_v_length, 0); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 191; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_6);
__pyx_v_last3 = ((PyObject*)__pyx_t_6);
__pyx_t_6 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":193
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* cdef unicode last3 = _substr(string, length - 3, length, length)
*
* assert normed # <<<<<<<<<<<<<<
* assert len(normed)
*
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
__pyx_t_5 = (__pyx_v_normed != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_normed) != 0);
if (unlikely(!__pyx_t_5)) {
PyErr_SetNone(PyExc_AssertionError);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 193; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
#endif
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":194
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* assert normed
* assert len(normed) # <<<<<<<<<<<<<<
*
* word.lex = hash_string(lex, len(lex))
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
if (unlikely(__pyx_v_normed == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 194; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_7 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_normed); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 194; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
if (unlikely(!(__pyx_t_7 != 0))) {
PyErr_SetNone(PyExc_AssertionError);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 194; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
}
#endif
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":196
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* assert len(normed)
*
* word.lex = hash_string(lex, len(lex)) # <<<<<<<<<<<<<<
* word.normed = hash_string(normed, len(normed))
* word.last3 = hash_string(last3, len(last3))
*/
if (unlikely(__pyx_v_lex == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 196; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_7 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_lex); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 196; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_8 = __pyx_f_5spacy_2en_hash_string(__pyx_v_lex, __pyx_t_7); if (unlikely(__pyx_t_8 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 196; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_word->lex = __pyx_t_8;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":197
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* word.lex = hash_string(lex, len(lex))
* word.normed = hash_string(normed, len(normed)) # <<<<<<<<<<<<<<
* word.last3 = hash_string(last3, len(last3))
*
*/
if (unlikely(__pyx_v_normed == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 197; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_7 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_normed); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 197; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_8 = __pyx_f_5spacy_2en_hash_string(__pyx_v_normed, __pyx_t_7); if (unlikely(__pyx_t_8 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 197; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_word->normed = __pyx_t_8;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":198
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* word.lex = hash_string(lex, len(lex))
* word.normed = hash_string(normed, len(normed))
* word.last3 = hash_string(last3, len(last3)) # <<<<<<<<<<<<<<
*
* STRINGS[word.lex] = lex
*/
if (unlikely(__pyx_v_last3 == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 198; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_7 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_last3); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 198; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_8 = __pyx_f_5spacy_2en_hash_string(__pyx_v_last3, __pyx_t_7); if (unlikely(__pyx_t_8 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 198; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_word->last3 = __pyx_t_8;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":200
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* word.last3 = hash_string(last3, len(last3))
*
* STRINGS[word.lex] = lex # <<<<<<<<<<<<<<
* STRINGS[word.normed] = normed
* STRINGS[word.last3] = last3
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = __Pyx_GetModuleGlobalName(__pyx_n_s_STRINGS); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 200; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_6);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(__Pyx_SetItemInt(__pyx_t_6, __pyx_v_word->lex, __pyx_v_lex, __pyx_t_5spacy_6lexeme_StringHash, 0, __Pyx_PyInt_From_uint64_t, 0, 0, 1) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 200; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":201
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* STRINGS[word.lex] = lex
* STRINGS[word.normed] = normed # <<<<<<<<<<<<<<
* STRINGS[word.last3] = last3
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = __Pyx_GetModuleGlobalName(__pyx_n_s_STRINGS); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 201; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_6);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(__Pyx_SetItemInt(__pyx_t_6, __pyx_v_word->normed, __pyx_v_normed, __pyx_t_5spacy_6lexeme_StringHash, 0, __Pyx_PyInt_From_uint64_t, 0, 0, 1) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 201; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":202
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* STRINGS[word.lex] = lex
* STRINGS[word.normed] = normed
* STRINGS[word.last3] = last3 # <<<<<<<<<<<<<<
*
* # These are loaded later
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_6 = __Pyx_GetModuleGlobalName(__pyx_n_s_STRINGS); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 202; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_6);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (unlikely(__Pyx_SetItemInt(__pyx_t_6, __pyx_v_word->last3, __pyx_v_last3, __pyx_t_5spacy_6lexeme_StringHash, 0, __Pyx_PyInt_From_uint64_t, 0, 0, 1) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 202; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":205
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* # These are loaded later
* word.prob = 0 # <<<<<<<<<<<<<<
* word.cluster = 0
* word.oft_upper = False
*/
__pyx_v_word->prob = 0.0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":206
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* # These are loaded later
* word.prob = 0
* word.cluster = 0 # <<<<<<<<<<<<<<
* word.oft_upper = False
* word.oft_title = False
*/
__pyx_v_word->cluster = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":207
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* word.prob = 0
* word.cluster = 0
* word.oft_upper = False # <<<<<<<<<<<<<<
* word.oft_title = False
*
*/
__pyx_v_word->oft_upper = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":208
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* word.cluster = 0
* word.oft_upper = False
* word.oft_title = False # <<<<<<<<<<<<<<
*
* # Now recurse, and deal with the tail
*/
__pyx_v_word->oft_title = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":211
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* # Now recurse, and deal with the tail
* if tail_string: # <<<<<<<<<<<<<<
* word.tail = <Lexeme*>lookup(tail_string)
* return word
*/
__pyx_t_5 = (__pyx_v_tail_string != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_tail_string) != 0);
if (__pyx_t_5) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":212
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* # Now recurse, and deal with the tail
* if tail_string:
* word.tail = <Lexeme*>lookup(tail_string) # <<<<<<<<<<<<<<
* return word
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_9 = __pyx_f_5spacy_2en_lookup(__pyx_v_tail_string, 0); if (unlikely(__pyx_t_9 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 212; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__pyx_v_word->tail = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_t_9);
goto __pyx_L4;
}
__pyx_L4:;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":213
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* if tail_string:
* word.tail = <Lexeme*>lookup(tail_string)
* return word # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = __pyx_v_word;
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":173
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef Lexeme* _init_lexeme(unicode string, StringHash hashed, # <<<<<<<<<<<<<<
* int split, size_t length) except NULL:
* assert split <= length
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_6);
__Pyx_AddTraceback("spacy.en._init_lexeme", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XDECREF(__pyx_v_tail_string);
__Pyx_XDECREF(__pyx_v_lex);
__Pyx_XDECREF(__pyx_v_normed);
__Pyx_XDECREF(__pyx_v_last3);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":216
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef size_t _find_split(unicode word, size_t length): # <<<<<<<<<<<<<<
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* cdef int i = 0
* # Contractions
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
static size_t __pyx_f_5spacy_2en__find_split(PyObject *__pyx_v_word, size_t __pyx_v_length) {
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
int __pyx_v_i;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
size_t __pyx_r;
__Pyx_RefNannyDeclarations
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
int __pyx_t_1;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
int __pyx_t_2;
int __pyx_t_3;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("_find_split", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":217
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* cdef size_t _find_split(unicode word, size_t length):
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* cdef int i = 0 # <<<<<<<<<<<<<<
* # Contractions
* if word.endswith("'s"):
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
__pyx_v_i = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":219
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* cdef int i = 0
* # Contractions
* if word.endswith("'s"): # <<<<<<<<<<<<<<
* return length - 2
* # Leading punctuation
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
if (unlikely(__pyx_v_word == Py_None)) {
PyErr_Format(PyExc_AttributeError, "'NoneType' object has no attribute '%s'", "endswith");
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 219; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_PyUnicode_Tailmatch(__pyx_v_word, __pyx_kp_u_s, 0, PY_SSIZE_T_MAX, 1); if (unlikely(__pyx_t_1 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 219; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
if ((__pyx_t_1 != 0)) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":220
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* # Contractions
* if word.endswith("'s"):
* return length - 2 # <<<<<<<<<<<<<<
* # Leading punctuation
* if is_punct(word, 0, length):
*/
__pyx_r = (__pyx_v_length - 2);
goto __pyx_L0;
}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":222
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* return length - 2
* # Leading punctuation
* if is_punct(word, 0, length): # <<<<<<<<<<<<<<
* return 1
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* elif length >= 1:
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_t_1 = (__pyx_f_5spacy_2en_is_punct(__pyx_v_word, 0, __pyx_v_length) != 0);
if (__pyx_t_1) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":223
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* # Leading punctuation
* if is_punct(word, 0, length):
* return 1 # <<<<<<<<<<<<<<
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* elif length >= 1:
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* # Split off all trailing punctuation characters
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_r = 1;
goto __pyx_L0;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":224
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* if is_punct(word, 0, length):
* return 1
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* elif length >= 1: # <<<<<<<<<<<<<<
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* # Split off all trailing punctuation characters
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* i = 0
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*/
__pyx_t_1 = ((__pyx_v_length >= 1) != 0);
if (__pyx_t_1) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":226
* elif length >= 1:
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* # Split off all trailing punctuation characters
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* i = 0 # <<<<<<<<<<<<<<
* while i < length and not is_punct(word, i, length):
* i += 1
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_v_i = 0;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":227
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* # Split off all trailing punctuation characters
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* i = 0
* while i < length and not is_punct(word, i, length): # <<<<<<<<<<<<<<
* i += 1
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* return i
*/
while (1) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = ((__pyx_v_i < __pyx_v_length) != 0);
if (__pyx_t_1) {
__pyx_t_2 = ((!(__pyx_f_5spacy_2en_is_punct(__pyx_v_word, __pyx_v_i, __pyx_v_length) != 0)) != 0);
__pyx_t_3 = __pyx_t_2;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
} else {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_3 = __pyx_t_1;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (!__pyx_t_3) break;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":228
* i = 0
* while i < length and not is_punct(word, i, length):
* i += 1 # <<<<<<<<<<<<<<
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* return i
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_v_i = (__pyx_v_i + 1);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
goto __pyx_L4;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_L4:;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":229
* while i < length and not is_punct(word, i, length):
* i += 1
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* return i # <<<<<<<<<<<<<<
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
__pyx_r = __pyx_v_i;
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":216
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef size_t _find_split(unicode word, size_t length): # <<<<<<<<<<<<<<
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* cdef int i = 0
* # Contractions
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_WriteUnraisable("spacy.en._find_split", __pyx_clineno, __pyx_lineno, __pyx_filename, 0);
__pyx_r = 0;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":232
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* cdef bint is_punct(unicode word, size_t i, size_t length): # <<<<<<<<<<<<<<
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* # Don't count appostrophes as punct if the next char is a letter
* if word[i] == "'" and i < (length - 1) and word[i+1].isalpha():
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static int __pyx_f_5spacy_2en_is_punct(PyObject *__pyx_v_word, size_t __pyx_v_i, size_t __pyx_v_length) {
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
int __pyx_r;
__Pyx_RefNannyDeclarations
Py_UCS4 __pyx_t_1;
int __pyx_t_2;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
int __pyx_t_3;
size_t __pyx_t_4;
int __pyx_t_5;
int __pyx_t_6;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("is_punct", 0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":234
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* cdef bint is_punct(unicode word, size_t i, size_t length):
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* # Don't count appostrophes as punct if the next char is a letter
* if word[i] == "'" and i < (length - 1) and word[i+1].isalpha(): # <<<<<<<<<<<<<<
* return False
* # Don't count commas as punct if the next char is a number
*/
__pyx_t_1 = __Pyx_GetItemInt_Unicode(__pyx_v_word, __pyx_v_i, size_t, 0, __Pyx_PyInt_FromSize_t, 0, 0, 1); if (unlikely(__pyx_t_1 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 234; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
__pyx_t_2 = (__pyx_t_1 == 39);
if (__pyx_t_2) {
__pyx_t_3 = (__pyx_v_i < (__pyx_v_length - 1));
if (__pyx_t_3) {
__pyx_t_4 = (__pyx_v_i + 1);
__pyx_t_1 = __Pyx_GetItemInt_Unicode(__pyx_v_word, __pyx_t_4, size_t, 0, __Pyx_PyInt_FromSize_t, 0, 0, 1); if (unlikely(__pyx_t_1 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 234; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
__pyx_t_5 = Py_UNICODE_ISALPHA(__pyx_t_1);
__pyx_t_6 = (__pyx_t_5 != 0);
} else {
__pyx_t_6 = __pyx_t_3;
}
__pyx_t_3 = __pyx_t_6;
} else {
__pyx_t_3 = __pyx_t_2;
}
if (__pyx_t_3) {
/* "spacy/en.pyx":235
* # Don't count appostrophes as punct if the next char is a letter
* if word[i] == "'" and i < (length - 1) and word[i+1].isalpha():
* return False # <<<<<<<<<<<<<<
* # Don't count commas as punct if the next char is a number
* if word[i] == "," and i < (length - 1) and word[i+1].isdigit():
*/
__pyx_r = 0;
goto __pyx_L0;
}
/* "spacy/en.pyx":237
* return False
* # Don't count commas as punct if the next char is a number
* if word[i] == "," and i < (length - 1) and word[i+1].isdigit(): # <<<<<<<<<<<<<<
* return False
* # Don't count periods as punct if the next char is a number
*/
__pyx_t_1 = __Pyx_GetItemInt_Unicode(__pyx_v_word, __pyx_v_i, size_t, 0, __Pyx_PyInt_FromSize_t, 0, 0, 1); if (unlikely(__pyx_t_1 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 237; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
__pyx_t_3 = (__pyx_t_1 == 44);
if (__pyx_t_3) {
__pyx_t_2 = (__pyx_v_i < (__pyx_v_length - 1));
if (__pyx_t_2) {
__pyx_t_4 = (__pyx_v_i + 1);
__pyx_t_1 = __Pyx_GetItemInt_Unicode(__pyx_v_word, __pyx_t_4, size_t, 0, __Pyx_PyInt_FromSize_t, 0, 0, 1); if (unlikely(__pyx_t_1 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 237; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
__pyx_t_6 = Py_UNICODE_ISDIGIT(__pyx_t_1);
__pyx_t_5 = (__pyx_t_6 != 0);
} else {
__pyx_t_5 = __pyx_t_2;
}
__pyx_t_2 = __pyx_t_5;
} else {
__pyx_t_2 = __pyx_t_3;
}
if (__pyx_t_2) {
/* "spacy/en.pyx":238
* # Don't count commas as punct if the next char is a number
* if word[i] == "," and i < (length - 1) and word[i+1].isdigit():
* return False # <<<<<<<<<<<<<<
* # Don't count periods as punct if the next char is a number
* if word[i] == "." and i < (length - 1) and word[i+1].isdigit():
*/
__pyx_r = 0;
goto __pyx_L0;
}
/* "spacy/en.pyx":240
* return False
* # Don't count periods as punct if the next char is a number
* if word[i] == "." and i < (length - 1) and word[i+1].isdigit(): # <<<<<<<<<<<<<<
* return False
* return not word[i].isalnum()
*/
__pyx_t_1 = __Pyx_GetItemInt_Unicode(__pyx_v_word, __pyx_v_i, size_t, 0, __Pyx_PyInt_FromSize_t, 0, 0, 1); if (unlikely(__pyx_t_1 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 240; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
__pyx_t_2 = (__pyx_t_1 == 46);
if (__pyx_t_2) {
__pyx_t_3 = (__pyx_v_i < (__pyx_v_length - 1));
if (__pyx_t_3) {
__pyx_t_4 = (__pyx_v_i + 1);
__pyx_t_1 = __Pyx_GetItemInt_Unicode(__pyx_v_word, __pyx_t_4, size_t, 0, __Pyx_PyInt_FromSize_t, 0, 0, 1); if (unlikely(__pyx_t_1 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 240; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
__pyx_t_5 = Py_UNICODE_ISDIGIT(__pyx_t_1);
__pyx_t_6 = (__pyx_t_5 != 0);
} else {
__pyx_t_6 = __pyx_t_3;
}
__pyx_t_3 = __pyx_t_6;
} else {
__pyx_t_3 = __pyx_t_2;
}
if (__pyx_t_3) {
/* "spacy/en.pyx":241
* # Don't count periods as punct if the next char is a number
* if word[i] == "." and i < (length - 1) and word[i+1].isdigit():
* return False # <<<<<<<<<<<<<<
* return not word[i].isalnum()
*/
__pyx_r = 0;
goto __pyx_L0;
}
/* "spacy/en.pyx":242
* if word[i] == "." and i < (length - 1) and word[i+1].isdigit():
* return False
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* return not word[i].isalnum() # <<<<<<<<<<<<<<
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_GetItemInt_Unicode(__pyx_v_word, __pyx_v_i, size_t, 0, __Pyx_PyInt_FromSize_t, 0, 0, 1); if (unlikely(__pyx_t_1 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 242; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
__pyx_t_3 = Py_UNICODE_ISALNUM(__pyx_t_1);
__pyx_r = (!(__pyx_t_3 != 0));
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
goto __pyx_L0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":232
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* cdef bint is_punct(unicode word, size_t i, size_t length): # <<<<<<<<<<<<<<
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
* # Don't count appostrophes as punct if the next char is a letter
* if word[i] == "'" and i < (length - 1) and word[i+1].isalpha():
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_WriteUnraisable("spacy.en.is_punct", __pyx_clineno, __pyx_lineno, __pyx_filename, 0);
__pyx_r = 0;
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "vector.to_py":63
*
* @cname("__pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr")
* cdef object __pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr(vector[X]& v): # <<<<<<<<<<<<<<
* return [X_to_py(v[i]) for i in range(v.size())]
*
*/
static PyObject *__pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr(const std::vector<__pyx_t_5spacy_2en_Lexeme_addr> &__pyx_v_v) {
size_t __pyx_v_i;
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
PyObject *__pyx_t_1 = NULL;
size_t __pyx_t_2;
size_t __pyx_t_3;
PyObject *__pyx_t_4 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("__pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr", 0);
/* "vector.to_py":64
* @cname("__pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr")
* cdef object __pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr(vector[X]& v):
* return [X_to_py(v[i]) for i in range(v.size())] # <<<<<<<<<<<<<<
*
*
*/
__Pyx_XDECREF(__pyx_r);
__pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 64; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_1);
__pyx_t_2 = __pyx_v_v.size();
for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) {
__pyx_v_i = __pyx_t_3;
__pyx_t_4 = __Pyx_PyInt_FromSize_t((__pyx_v_v[__pyx_v_i])); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 64; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_4);
if (unlikely(__Pyx_ListComp_Append(__pyx_t_1, (PyObject*)__pyx_t_4))) {__pyx_filename = __pyx_f[1]; __pyx_lineno = 64; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
}
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* "vector.to_py":63
*
* @cname("__pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr")
* cdef object __pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr(vector[X]& v): # <<<<<<<<<<<<<<
* return [X_to_py(v[i]) for i in range(v.size())]
*
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_XDECREF(__pyx_t_4);
__Pyx_AddTraceback("vector.to_py.__pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = 0;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyMethodDef __pyx_methods[] = {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{__Pyx_NAMESTR("tokenize"), (PyCFunction)__pyx_pw_5spacy_2en_3tokenize, METH_O, __Pyx_DOCSTR(0)},
{__Pyx_NAMESTR("lookup"), (PyCFunction)__pyx_pw_5spacy_2en_5lookup, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_2en_4lookup)},
{__Pyx_NAMESTR("lookup_chunk"), (PyCFunction)__pyx_pw_5spacy_2en_7lookup_chunk, METH_VARARGS|METH_KEYWORDS, __Pyx_DOCSTR(__pyx_doc_5spacy_2en_6lookup_chunk)},
{__Pyx_NAMESTR("unhash"), (PyCFunction)__pyx_pw_5spacy_2en_9unhash, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_2en_8unhash)},
{__Pyx_NAMESTR("_substr"), (PyCFunction)__pyx_pw_5spacy_2en_11_substr, METH_VARARGS|METH_KEYWORDS, __Pyx_DOCSTR(0)},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{0, 0, 0, 0}
};
#if PY_MAJOR_VERSION >= 3
static struct PyModuleDef __pyx_moduledef = {
#if PY_VERSION_HEX < 0x03020000
{ PyObject_HEAD_INIT(NULL) NULL, 0, NULL },
#else
PyModuleDef_HEAD_INIT,
#endif
__Pyx_NAMESTR("en"),
__Pyx_DOCSTR(__pyx_k_Serve_pointers_to_Lexeme_structs), /* m_doc */
-1, /* m_size */
__pyx_methods /* m_methods */,
NULL, /* m_reload */
NULL, /* m_traverse */
NULL, /* m_clear */
NULL /* m_free */
};
#endif
static __Pyx_StringTabEntry __pyx_string_tab[] = {
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_s_, __pyx_k_, sizeof(__pyx_k_), 0, 0, 1, 1},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_kp_u_, __pyx_k_, sizeof(__pyx_k_), 0, 1, 0, 0},
{&__pyx_kp_u_DIGITS, __pyx_k_DIGITS, sizeof(__pyx_k_DIGITS), 0, 1, 0, 0},
{&__pyx_n_s_LEXEMES, __pyx_k_LEXEMES, sizeof(__pyx_k_LEXEMES), 0, 0, 1, 1},
{&__pyx_n_s_STRINGS, __pyx_k_STRINGS, sizeof(__pyx_k_STRINGS), 0, 0, 1, 1},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_kp_s_Users_matt_repos_spaCy_spacy_en, __pyx_k_Users_matt_repos_spaCy_spacy_en, sizeof(__pyx_k_Users_matt_repos_spaCy_spacy_en), 0, 0, 1, 0},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_ValueError, __pyx_k_ValueError, sizeof(__pyx_k_ValueError), 0, 0, 1, 1},
{&__pyx_kp_u_YEAR, __pyx_k_YEAR, sizeof(__pyx_k_YEAR), 0, 1, 0, 0},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_s_chunk, __pyx_k_chunk, sizeof(__pyx_k_chunk), 0, 0, 1, 1},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_cluster, __pyx_k_cluster, sizeof(__pyx_k_cluster), 0, 0, 1, 1},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_u_en, __pyx_k_en, sizeof(__pyx_k_en), 0, 1, 0, 1},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_end, __pyx_k_end, sizeof(__pyx_k_end), 0, 0, 1, 1},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_s_enumerate, __pyx_k_enumerate, sizeof(__pyx_k_enumerate), 0, 0, 1, 1},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_first, __pyx_k_first, sizeof(__pyx_k_first), 0, 0, 1, 1},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_s_hashed, __pyx_k_hashed, sizeof(__pyx_k_hashed), 0, 0, 1, 1},
{&__pyx_n_s_i, __pyx_k_i, sizeof(__pyx_k_i), 0, 0, 1, 1},
{&__pyx_n_s_import, __pyx_k_import, sizeof(__pyx_k_import), 0, 0, 1, 1},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_isdigit, __pyx_k_isdigit, sizeof(__pyx_k_isdigit), 0, 0, 1, 1},
{&__pyx_n_s_last3, __pyx_k_last3, sizeof(__pyx_k_last3), 0, 0, 1, 1},
{&__pyx_n_s_length, __pyx_k_length, sizeof(__pyx_k_length), 0, 0, 1, 1},
{&__pyx_n_s_lex, __pyx_k_lex, sizeof(__pyx_k_lex), 0, 0, 1, 1},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_s_load_tokenization, __pyx_k_load_tokenization, sizeof(__pyx_k_load_tokenization), 0, 0, 1, 1},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_lower, __pyx_k_lower, sizeof(__pyx_k_lower), 0, 0, 1, 1},
{&__pyx_n_s_main, __pyx_k_main, sizeof(__pyx_k_main), 0, 0, 1, 1},
{&__pyx_n_s_normed, __pyx_k_normed, sizeof(__pyx_k_normed), 0, 0, 1, 1},
{&__pyx_n_s_oft_title, __pyx_k_oft_title, sizeof(__pyx_k_oft_title), 0, 0, 1, 1},
{&__pyx_n_s_oft_upper, __pyx_k_oft_upper, sizeof(__pyx_k_oft_upper), 0, 0, 1, 1},
{&__pyx_n_s_prob, __pyx_k_prob, sizeof(__pyx_k_prob), 0, 0, 1, 1},
{&__pyx_n_s_pyx_capi, __pyx_k_pyx_capi, sizeof(__pyx_k_pyx_capi), 0, 0, 1, 1},
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
{&__pyx_n_s_range, __pyx_k_range, sizeof(__pyx_k_range), 0, 0, 1, 1},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_s_read_tokenization, __pyx_k_read_tokenization, sizeof(__pyx_k_read_tokenization), 0, 0, 1, 1},
{&__pyx_kp_u_s, __pyx_k_s, sizeof(__pyx_k_s), 0, 1, 0, 0},
{&__pyx_kp_u_s_d_s, __pyx_k_s_d_s, sizeof(__pyx_k_s_d_s), 0, 1, 0, 0},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_sic, __pyx_k_sic, sizeof(__pyx_k_sic), 0, 0, 1, 1},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_s_spacy_en, __pyx_k_spacy_en, sizeof(__pyx_k_spacy_en), 0, 0, 1, 1},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_start, __pyx_k_start, sizeof(__pyx_k_start), 0, 0, 1, 1},
{&__pyx_n_s_string, __pyx_k_string, sizeof(__pyx_k_string), 0, 0, 1, 1},
{&__pyx_n_s_tail, __pyx_k_tail, sizeof(__pyx_k_tail), 0, 0, 1, 1},
{&__pyx_n_s_test, __pyx_k_test, sizeof(__pyx_k_test), 0, 0, 1, 1},
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
{&__pyx_n_s_token_rules, __pyx_k_token_rules, sizeof(__pyx_k_token_rules), 0, 0, 1, 1},
{&__pyx_n_s_token_string, __pyx_k_token_string, sizeof(__pyx_k_token_string), 0, 0, 1, 1},
{&__pyx_n_s_tokens, __pyx_k_tokens, sizeof(__pyx_k_tokens), 0, 0, 1, 1},
{&__pyx_n_s_util, __pyx_k_util, sizeof(__pyx_k_util), 0, 0, 1, 1},
{&__pyx_n_s_word, __pyx_k_word, sizeof(__pyx_k_word), 0, 0, 1, 1},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{0, 0, 0, 0, 0, 0, 0}
};
static int __Pyx_InitCachedBuiltins(void) {
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 32; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 53; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 130; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return 0;
__pyx_L1_error:;
return -1;
}
static int __Pyx_InitCachedConstants(void) {
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0);
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":25
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* def load_tokenization(token_rules): # <<<<<<<<<<<<<<
* cdef Lexeme* word
* cdef StringHash hashed
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_tuple__2 = PyTuple_Pack(9, __pyx_n_s_token_rules, __pyx_n_s_word, __pyx_n_s_hashed, __pyx_n_s_chunk, __pyx_n_s_lex, __pyx_n_s_tokens, __pyx_n_s_i, __pyx_n_s_token_string, __pyx_n_s_length); if (unlikely(!__pyx_tuple__2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 25; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_tuple__2);
__Pyx_GIVEREF(__pyx_tuple__2);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_codeobj__3 = (PyObject*)__Pyx_PyCode_New(1, 0, 9, 0, 0, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__2, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_Users_matt_repos_spaCy_spacy_en, __pyx_n_s_load_tokenization, 25, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__3)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 25; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":40
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* load_tokenization(util.read_tokenization('en')) # <<<<<<<<<<<<<<
*
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
*
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_tuple__4 = PyTuple_Pack(1, __pyx_n_u_en); if (unlikely(!__pyx_tuple__4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 40; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_tuple__4);
__Pyx_GIVEREF(__pyx_tuple__4);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_RefNannyFinishContext();
return 0;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_L1_error:;
__Pyx_RefNannyFinishContext();
return -1;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
static int __Pyx_InitGlobals(void) {
if (__Pyx_InitStrings(__pyx_string_tab) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_int_0 = PyInt_FromLong(0); if (unlikely(!__pyx_int_0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_int_1 = PyInt_FromLong(1); if (unlikely(!__pyx_int_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return 0;
__pyx_L1_error:;
return -1;
}
#if PY_MAJOR_VERSION < 3
PyMODINIT_FUNC initen(void); /*proto*/
PyMODINIT_FUNC initen(void)
#else
PyMODINIT_FUNC PyInit_en(void); /*proto*/
PyMODINIT_FUNC PyInit_en(void)
#endif
{
PyObject *__pyx_t_1 = NULL;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
PyObject *__pyx_t_2 = NULL;
struct __pyx_t_5spacy_6lexeme_Lexeme __pyx_t_3;
PyObject *__pyx_t_4 = NULL;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannyDeclarations
#if CYTHON_REFNANNY
__Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny");
if (!__Pyx_RefNanny) {
PyErr_Clear();
__Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny");
if (!__Pyx_RefNanny)
Py_FatalError("failed to import 'refnanny' module");
}
#endif
__Pyx_RefNannySetupContext("PyMODINIT_FUNC PyInit_en(void)", 0);
if ( __Pyx_check_binary_version() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#ifdef __Pyx_CyFunction_USED
if (__Pyx_CyFunction_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#endif
#ifdef __Pyx_FusedFunction_USED
if (__pyx_FusedFunction_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#endif
#ifdef __Pyx_Generator_USED
if (__pyx_Generator_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#endif
/*--- Library function declarations ---*/
/*--- Threads initialization code ---*/
#if defined(__PYX_FORCE_INIT_THREADS) && __PYX_FORCE_INIT_THREADS
#ifdef WITH_THREAD /* Python build with threading support? */
PyEval_InitThreads();
#endif
#endif
/*--- Module creation code ---*/
#if PY_MAJOR_VERSION < 3
__pyx_m = Py_InitModule4(__Pyx_NAMESTR("en"), __pyx_methods, __Pyx_DOCSTR(__pyx_k_Serve_pointers_to_Lexeme_structs), 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m);
#else
__pyx_m = PyModule_Create(&__pyx_moduledef);
#endif
if (unlikely(!__pyx_m)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_d = PyModule_GetDict(__pyx_m); if (unlikely(!__pyx_d)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
Py_INCREF(__pyx_d);
__pyx_b = PyImport_AddModule(__Pyx_NAMESTR(__Pyx_BUILTIN_MODULE_NAME)); if (unlikely(!__pyx_b)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#if CYTHON_COMPILING_IN_PYPY
Py_INCREF(__pyx_b);
#endif
if (__Pyx_SetAttrString(__pyx_m, "__builtins__", __pyx_b) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
/*--- Initialize various global constants etc. ---*/
if (unlikely(__Pyx_InitGlobals() < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#if PY_MAJOR_VERSION < 3 && (__PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT)
if (__Pyx_init_sys_getdefaultencoding_params() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#endif
if (__pyx_module_is_main_spacy__en) {
if (__Pyx_SetAttrString(__pyx_m, "__name__", __pyx_n_s_main) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
}
#if PY_MAJOR_VERSION >= 3
{
PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (!PyDict_GetItemString(modules, "spacy.en")) {
if (unlikely(PyDict_SetItemString(modules, "spacy.en", __pyx_m) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
}
#endif
/*--- Builtin init code ---*/
if (unlikely(__Pyx_InitCachedBuiltins() < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
/*--- Constants init code ---*/
if (unlikely(__Pyx_InitCachedConstants() < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
/*--- Global init code ---*/
/*--- Variable export code ---*/
if (__Pyx_ExportVoidPtr(__pyx_n_s_LEXEMES, (void *)&__pyx_v_5spacy_2en_LEXEMES, "google::dense_hash_map<__pyx_t_5spacy_6lexeme_StringHash,__pyx_t_5spacy_2en_Lexeme_ptr>") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
/*--- Function export code ---*/
if (__Pyx_ExportFunction("lookup", (void (*)(void))__pyx_f_5spacy_2en_lookup, "__pyx_t_5spacy_2en_Lexeme_addr (PyObject *, int __pyx_skip_dispatch)") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (__Pyx_ExportFunction("lookup_chunk", (void (*)(void))__pyx_f_5spacy_2en_lookup_chunk, "__pyx_t_5spacy_2en_Lexeme_addr (PyObject *, int, int, int __pyx_skip_dispatch)") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (__Pyx_ExportFunction("hash_string", (void (*)(void))__pyx_f_5spacy_2en_hash_string, "__pyx_t_5spacy_6lexeme_StringHash (PyObject *, size_t)") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (__Pyx_ExportFunction("unhash", (void (*)(void))__pyx_f_5spacy_2en_unhash, "PyObject *(__pyx_t_5spacy_6lexeme_StringHash, int __pyx_skip_dispatch)") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
/*--- Type init code ---*/
/*--- Type import code ---*/
/*--- Variable import code ---*/
/*--- Function import code ---*/
/*--- Execution code ---*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":14
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
* from ext.murmurhash cimport MurmurHash64A
* from ext.murmurhash cimport MurmurHash64B
* from . import util # <<<<<<<<<<<<<<
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 14; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_1);
__Pyx_INCREF(__pyx_n_s_util);
PyList_SET_ITEM(__pyx_t_1, 0, __pyx_n_s_util);
__Pyx_GIVEREF(__pyx_n_s_util);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __Pyx_Import(__pyx_n_s_, __pyx_t_1, 1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 14; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_2);
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_util); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 14; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (PyDict_SetItem(__pyx_d, __pyx_n_s_util, __pyx_t_1) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 14; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":17
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
* STRINGS = {} # <<<<<<<<<<<<<<
* LEXEMES = dense_hash_map[StringHash, Lexeme_ptr]()
* LEXEMES.set_empty_key(0)
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = PyDict_New(); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 17; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_2);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (PyDict_SetItem(__pyx_d, __pyx_n_s_STRINGS, __pyx_t_2) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 17; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":18
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* STRINGS = {}
* LEXEMES = dense_hash_map[StringHash, Lexeme_ptr]() # <<<<<<<<<<<<<<
* LEXEMES.set_empty_key(0)
*
*/
__pyx_v_5spacy_2en_LEXEMES = google::dense_hash_map<__pyx_t_5spacy_6lexeme_StringHash,__pyx_t_5spacy_2en_Lexeme_ptr>();
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":19
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* STRINGS = {}
* LEXEMES = dense_hash_map[StringHash, Lexeme_ptr]()
* LEXEMES.set_empty_key(0) # <<<<<<<<<<<<<<
*
*
*/
__pyx_v_5spacy_2en_LEXEMES.set_empty_key(0);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":22
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cdef Lexeme BLANK_WORD = Lexeme(0, 0, 0, 0, 0, 0.0, 0, False, False, NULL) # <<<<<<<<<<<<<<
*
*
*/
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__pyx_t_3.sic = 0;
__pyx_t_3.lex = 0;
__pyx_t_3.normed = 0;
__pyx_t_3.last3 = 0;
__pyx_t_3.first = 0;
__pyx_t_3.prob = 0.0;
__pyx_t_3.cluster = 0;
__pyx_t_3.oft_upper = 0;
__pyx_t_3.oft_title = 0;
__pyx_t_3.tail = NULL;
__pyx_v_5spacy_2en_BLANK_WORD = __pyx_t_3;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":25
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* def load_tokenization(token_rules): # <<<<<<<<<<<<<<
* cdef Lexeme* word
* cdef StringHash hashed
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = PyCFunction_NewEx(&__pyx_mdef_5spacy_2en_1load_tokenization, NULL, __pyx_n_s_spacy_en); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 25; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_2);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
if (PyDict_SetItem(__pyx_d, __pyx_n_s_load_tokenization, __pyx_t_2) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 25; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "spacy/en.pyx":40
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*
*
* load_tokenization(util.read_tokenization('en')) # <<<<<<<<<<<<<<
*
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
*
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
*/
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_load_tokenization); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 40; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_2);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_util); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 40; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_1);
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_read_tokenization); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 40; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_4);
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 40; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_1);
__Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_4 = PyTuple_New(1); if (unlikely(!__pyx_t_4)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 40; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_4);
PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_1);
__Pyx_GIVEREF(__pyx_t_1);
__pyx_t_1 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
__pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_4, NULL); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 40; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_GOTREF(__pyx_t_1);
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
__Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0;
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/* "spacy/en.pyx":1
* '''Serve pointers to Lexeme structs, given strings. Maintain a reverse index, # <<<<<<<<<<<<<<
* so that strings can be retrieved from hashes. Use 64-bit hash values and
* boldly assume no collisions.
*/
__pyx_t_1 = PyDict_New(); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_1);
if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_1) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
/* "vector.to_py":63
*
* @cname("__pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr")
* cdef object __pyx_convert_vector_to_py___pyx_t_5spacy_2en_Lexeme_addr(vector[X]& v): # <<<<<<<<<<<<<<
* return [X_to_py(v[i]) for i in range(v.size())]
*
*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
goto __pyx_L0;
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
__Pyx_XDECREF(__pyx_t_2);
__Pyx_XDECREF(__pyx_t_4);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
if (__pyx_m) {
__Pyx_AddTraceback("init spacy.en", __pyx_clineno, __pyx_lineno, __pyx_filename);
Py_DECREF(__pyx_m); __pyx_m = 0;
} else if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ImportError, "init spacy.en");
}
__pyx_L0:;
__Pyx_RefNannyFinishContext();
#if PY_MAJOR_VERSION < 3
return;
#else
return __pyx_m;
#endif
}
/* Runtime support code */
#if CYTHON_REFNANNY
static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) {
PyObject *m = NULL, *p = NULL;
void *r = NULL;
m = PyImport_ImportModule((char *)modname);
if (!m) goto end;
p = PyObject_GetAttrString(m, (char *)"RefNannyAPI");
if (!p) goto end;
r = PyLong_AsVoidPtr(p);
end:
Py_XDECREF(p);
Py_XDECREF(m);
return (__Pyx_RefNannyAPIStruct *)r;
}
#endif /* CYTHON_REFNANNY */
static PyObject *__Pyx_GetBuiltinName(PyObject *name) {
PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name);
if (unlikely(!result)) {
PyErr_Format(PyExc_NameError,
#if PY_MAJOR_VERSION >= 3
"name '%U' is not defined", name);
#else
"name '%.200s' is not defined", PyString_AS_STRING(name));
#endif
}
return result;
}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) {
PyErr_Format(PyExc_ValueError,
"too many values to unpack (expected %" CYTHON_FORMAT_SSIZE_T "d)", expected);
}
static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) {
PyErr_Format(PyExc_ValueError,
"need more than %" CYTHON_FORMAT_SSIZE_T "d value%.1s to unpack",
index, (index == 1) ? "" : "s");
}
static CYTHON_INLINE int __Pyx_IterFinish(void) {
#if CYTHON_COMPILING_IN_CPYTHON
PyThreadState *tstate = PyThreadState_GET();
PyObject* exc_type = tstate->curexc_type;
if (unlikely(exc_type)) {
if (likely(exc_type == PyExc_StopIteration) || PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration)) {
PyObject *exc_value, *exc_tb;
exc_value = tstate->curexc_value;
exc_tb = tstate->curexc_traceback;
tstate->curexc_type = 0;
tstate->curexc_value = 0;
tstate->curexc_traceback = 0;
Py_DECREF(exc_type);
Py_XDECREF(exc_value);
Py_XDECREF(exc_tb);
return 0;
} else {
return -1;
}
}
return 0;
#else
if (unlikely(PyErr_Occurred())) {
if (likely(PyErr_ExceptionMatches(PyExc_StopIteration))) {
PyErr_Clear();
return 0;
} else {
return -1;
}
}
return 0;
#endif
}
static int __Pyx_IternextUnpackEndCheck(PyObject *retval, Py_ssize_t expected) {
if (unlikely(retval)) {
Py_DECREF(retval);
__Pyx_RaiseTooManyValuesError(expected);
return -1;
} else {
return __Pyx_IterFinish();
}
return 0;
}
* Working tokenization. en doesn't match PTB perfectly. Need to reorganize before adding more schemes.
2014-07-07 03:15:59 +04:00
static void __Pyx_RaiseArgumentTypeInvalid(const char* name, PyObject *obj, PyTypeObject *type) {
PyErr_Format(PyExc_TypeError,
"Argument '%.200s' has incorrect type (expected %.200s, got %.200s)",
name, type->tp_name, Py_TYPE(obj)->tp_name);
}
static CYTHON_INLINE int __Pyx_ArgTypeTest(PyObject *obj, PyTypeObject *type, int none_allowed,
const char *name, int exact)
{
if (unlikely(!type)) {
PyErr_SetString(PyExc_SystemError, "Missing type object");
return 0;
}
if (none_allowed && obj == Py_None) return 1;
else if (exact) {
if (likely(Py_TYPE(obj) == type)) return 1;
#if PY_MAJOR_VERSION == 2
else if ((type == &PyBaseString_Type) && likely(__Pyx_PyBaseString_CheckExact(obj))) return 1;
#endif
}
else {
if (likely(PyObject_TypeCheck(obj, type))) return 1;
}
__Pyx_RaiseArgumentTypeInvalid(name, obj, type);
return 0;
}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static CYTHON_INLINE int __Pyx_PyBytes_Equals(PyObject* s1, PyObject* s2, int equals) {
#if CYTHON_COMPILING_IN_PYPY
return PyObject_RichCompareBool(s1, s2, equals);
#else
if (s1 == s2) {
return (equals == Py_EQ);
} else if (PyBytes_CheckExact(s1) & PyBytes_CheckExact(s2)) {
const char *ps1, *ps2;
Py_ssize_t length = PyBytes_GET_SIZE(s1);
if (length != PyBytes_GET_SIZE(s2))
return (equals == Py_NE);
ps1 = PyBytes_AS_STRING(s1);
ps2 = PyBytes_AS_STRING(s2);
if (ps1[0] != ps2[0]) {
return (equals == Py_NE);
} else if (length == 1) {
return (equals == Py_EQ);
} else {
int result = memcmp(ps1, ps2, (size_t)length);
return (equals == Py_EQ) ? (result == 0) : (result != 0);
}
} else if ((s1 == Py_None) & PyBytes_CheckExact(s2)) {
return (equals == Py_NE);
} else if ((s2 == Py_None) & PyBytes_CheckExact(s1)) {
return (equals == Py_NE);
} else {
int result;
PyObject* py_result = PyObject_RichCompare(s1, s2, equals);
if (!py_result)
return -1;
result = __Pyx_PyObject_IsTrue(py_result);
Py_DECREF(py_result);
return result;
}
#endif
}
static CYTHON_INLINE int __Pyx_PyUnicode_Equals(PyObject* s1, PyObject* s2, int equals) {
#if CYTHON_COMPILING_IN_PYPY
return PyObject_RichCompareBool(s1, s2, equals);
#else
#if PY_MAJOR_VERSION < 3
PyObject* owned_ref = NULL;
#endif
int s1_is_unicode, s2_is_unicode;
if (s1 == s2) {
goto return_eq;
}
s1_is_unicode = PyUnicode_CheckExact(s1);
s2_is_unicode = PyUnicode_CheckExact(s2);
#if PY_MAJOR_VERSION < 3
if ((s1_is_unicode & (!s2_is_unicode)) && PyString_CheckExact(s2)) {
owned_ref = PyUnicode_FromObject(s2);
if (unlikely(!owned_ref))
return -1;
s2 = owned_ref;
s2_is_unicode = 1;
} else if ((s2_is_unicode & (!s1_is_unicode)) && PyString_CheckExact(s1)) {
owned_ref = PyUnicode_FromObject(s1);
if (unlikely(!owned_ref))
return -1;
s1 = owned_ref;
s1_is_unicode = 1;
} else if (((!s2_is_unicode) & (!s1_is_unicode))) {
return __Pyx_PyBytes_Equals(s1, s2, equals);
}
#endif
if (s1_is_unicode & s2_is_unicode) {
Py_ssize_t length;
int kind;
void *data1, *data2;
#if CYTHON_PEP393_ENABLED
if (unlikely(PyUnicode_READY(s1) < 0) || unlikely(PyUnicode_READY(s2) < 0))
return -1;
#endif
length = __Pyx_PyUnicode_GET_LENGTH(s1);
if (length != __Pyx_PyUnicode_GET_LENGTH(s2)) {
goto return_ne;
}
kind = __Pyx_PyUnicode_KIND(s1);
if (kind != __Pyx_PyUnicode_KIND(s2)) {
goto return_ne;
}
data1 = __Pyx_PyUnicode_DATA(s1);
data2 = __Pyx_PyUnicode_DATA(s2);
if (__Pyx_PyUnicode_READ(kind, data1, 0) != __Pyx_PyUnicode_READ(kind, data2, 0)) {
goto return_ne;
} else if (length == 1) {
goto return_eq;
} else {
int result = memcmp(data1, data2, length * kind);
#if PY_MAJOR_VERSION < 3
Py_XDECREF(owned_ref);
#endif
return (equals == Py_EQ) ? (result == 0) : (result != 0);
}
} else if ((s1 == Py_None) & s2_is_unicode) {
goto return_ne;
} else if ((s2 == Py_None) & s1_is_unicode) {
goto return_ne;
} else {
int result;
PyObject* py_result = PyObject_RichCompare(s1, s2, equals);
if (!py_result)
return -1;
result = __Pyx_PyObject_IsTrue(py_result);
Py_DECREF(py_result);
return result;
}
return_eq:
#if PY_MAJOR_VERSION < 3
Py_XDECREF(owned_ref);
#endif
return (equals == Py_EQ);
return_ne:
#if PY_MAJOR_VERSION < 3
Py_XDECREF(owned_ref);
#endif
return (equals == Py_NE);
#endif
}
static void __Pyx_RaiseArgtupleInvalid(
const char* func_name,
int exact,
Py_ssize_t num_min,
Py_ssize_t num_max,
Py_ssize_t num_found)
{
Py_ssize_t num_expected;
const char *more_or_less;
if (num_found < num_min) {
num_expected = num_min;
more_or_less = "at least";
} else {
num_expected = num_max;
more_or_less = "at most";
}
if (exact) {
more_or_less = "exactly";
}
PyErr_Format(PyExc_TypeError,
"%.200s() takes %.8s %" CYTHON_FORMAT_SSIZE_T "d positional argument%.1s (%" CYTHON_FORMAT_SSIZE_T "d given)",
func_name, more_or_less, num_expected,
(num_expected == 1) ? "" : "s", num_found);
}
static void __Pyx_RaiseDoubleKeywordsError(
const char* func_name,
PyObject* kw_name)
{
PyErr_Format(PyExc_TypeError,
#if PY_MAJOR_VERSION >= 3
"%s() got multiple values for keyword argument '%U'", func_name, kw_name);
#else
"%s() got multiple values for keyword argument '%s'", func_name,
PyString_AsString(kw_name));
#endif
}
static int __Pyx_ParseOptionalKeywords(
PyObject *kwds,
PyObject **argnames[],
PyObject *kwds2,
PyObject *values[],
Py_ssize_t num_pos_args,
const char* function_name)
{
PyObject *key = 0, *value = 0;
Py_ssize_t pos = 0;
PyObject*** name;
PyObject*** first_kw_arg = argnames + num_pos_args;
while (PyDict_Next(kwds, &pos, &key, &value)) {
name = first_kw_arg;
while (*name && (**name != key)) name++;
if (*name) {
values[name-argnames] = value;
continue;
}
name = first_kw_arg;
#if PY_MAJOR_VERSION < 3
if (likely(PyString_CheckExact(key)) || likely(PyString_Check(key))) {
while (*name) {
if ((CYTHON_COMPILING_IN_PYPY || PyString_GET_SIZE(**name) == PyString_GET_SIZE(key))
&& _PyString_Eq(**name, key)) {
values[name-argnames] = value;
break;
}
name++;
}
if (*name) continue;
else {
PyObject*** argname = argnames;
while (argname != first_kw_arg) {
if ((**argname == key) || (
(CYTHON_COMPILING_IN_PYPY || PyString_GET_SIZE(**argname) == PyString_GET_SIZE(key))
&& _PyString_Eq(**argname, key))) {
goto arg_passed_twice;
}
argname++;
}
}
} else
#endif
if (likely(PyUnicode_Check(key))) {
while (*name) {
int cmp = (**name == key) ? 0 :
#if !CYTHON_COMPILING_IN_PYPY && PY_MAJOR_VERSION >= 3
(PyUnicode_GET_SIZE(**name) != PyUnicode_GET_SIZE(key)) ? 1 :
#endif
PyUnicode_Compare(**name, key);
if (cmp < 0 && unlikely(PyErr_Occurred())) goto bad;
if (cmp == 0) {
values[name-argnames] = value;
break;
}
name++;
}
if (*name) continue;
else {
PyObject*** argname = argnames;
while (argname != first_kw_arg) {
int cmp = (**argname == key) ? 0 :
#if !CYTHON_COMPILING_IN_PYPY && PY_MAJOR_VERSION >= 3
(PyUnicode_GET_SIZE(**argname) != PyUnicode_GET_SIZE(key)) ? 1 :
#endif
PyUnicode_Compare(**argname, key);
if (cmp < 0 && unlikely(PyErr_Occurred())) goto bad;
if (cmp == 0) goto arg_passed_twice;
argname++;
}
}
} else
goto invalid_keyword_type;
if (kwds2) {
if (unlikely(PyDict_SetItem(kwds2, key, value))) goto bad;
} else {
goto invalid_keyword;
}
}
return 0;
arg_passed_twice:
__Pyx_RaiseDoubleKeywordsError(function_name, key);
goto bad;
invalid_keyword_type:
PyErr_Format(PyExc_TypeError,
"%.200s() keywords must be strings", function_name);
goto bad;
invalid_keyword:
PyErr_Format(PyExc_TypeError,
#if PY_MAJOR_VERSION < 3
"%.200s() got an unexpected keyword argument '%.200s'",
function_name, PyString_AsString(key));
#else
"%s() got an unexpected keyword argument '%U'",
function_name, key);
#endif
bad:
return -1;
}
static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) {
PyObject *result;
#if CYTHON_COMPILING_IN_CPYTHON
result = PyDict_GetItem(__pyx_d, name);
if (result) {
Py_INCREF(result);
} else {
#else
result = PyObject_GetItem(__pyx_d, name);
if (!result) {
PyErr_Clear();
#endif
result = __Pyx_GetBuiltinName(name);
}
return result;
}
static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) {
PyObject *r;
if (!j) return NULL;
r = PyObject_GetItem(o, j);
Py_DECREF(j);
return r;
}
static CYTHON_INLINE PyObject *__Pyx_GetItemInt_List_Fast(PyObject *o, Py_ssize_t i,
int wraparound, int boundscheck) {
#if CYTHON_COMPILING_IN_CPYTHON
if (wraparound & unlikely(i < 0)) i += PyList_GET_SIZE(o);
if ((!boundscheck) || likely((0 <= i) & (i < PyList_GET_SIZE(o)))) {
PyObject *r = PyList_GET_ITEM(o, i);
Py_INCREF(r);
return r;
}
return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i));
#else
return PySequence_GetItem(o, i);
#endif
}
static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Tuple_Fast(PyObject *o, Py_ssize_t i,
int wraparound, int boundscheck) {
#if CYTHON_COMPILING_IN_CPYTHON
if (wraparound & unlikely(i < 0)) i += PyTuple_GET_SIZE(o);
if ((!boundscheck) || likely((0 <= i) & (i < PyTuple_GET_SIZE(o)))) {
PyObject *r = PyTuple_GET_ITEM(o, i);
Py_INCREF(r);
return r;
}
return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i));
#else
return PySequence_GetItem(o, i);
#endif
}
static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i,
int is_list, int wraparound, int boundscheck) {
#if CYTHON_COMPILING_IN_CPYTHON
if (is_list || PyList_CheckExact(o)) {
Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyList_GET_SIZE(o);
if ((!boundscheck) || (likely((n >= 0) & (n < PyList_GET_SIZE(o))))) {
PyObject *r = PyList_GET_ITEM(o, n);
Py_INCREF(r);
return r;
}
}
else if (PyTuple_CheckExact(o)) {
Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyTuple_GET_SIZE(o);
if ((!boundscheck) || likely((n >= 0) & (n < PyTuple_GET_SIZE(o)))) {
PyObject *r = PyTuple_GET_ITEM(o, n);
Py_INCREF(r);
return r;
}
} else {
PySequenceMethods *m = Py_TYPE(o)->tp_as_sequence;
if (likely(m && m->sq_item)) {
if (wraparound && unlikely(i < 0) && likely(m->sq_length)) {
Py_ssize_t l = m->sq_length(o);
if (likely(l >= 0)) {
i += l;
} else {
if (PyErr_ExceptionMatches(PyExc_OverflowError))
PyErr_Clear();
else
return NULL;
}
}
return m->sq_item(o, i);
}
}
#else
if (is_list || PySequence_Check(o)) {
return PySequence_GetItem(o, i);
}
#endif
return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i));
}
#if CYTHON_COMPILING_IN_CPYTHON
static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg, PyObject *kw) {
PyObject *result;
ternaryfunc call = func->ob_type->tp_call;
if (unlikely(!call))
return PyObject_Call(func, arg, kw);
#if PY_VERSION_HEX >= 0x02060000
if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object")))
return NULL;
#endif
result = (*call)(func, arg, kw);
#if PY_VERSION_HEX >= 0x02060000
Py_LeaveRecursiveCall();
#endif
if (unlikely(!result) && unlikely(!PyErr_Occurred())) {
PyErr_SetString(
PyExc_SystemError,
"NULL result without error in PyObject_Call");
}
return result;
}
#endif
static CYTHON_INLINE void __Pyx_ErrRestore(PyObject *type, PyObject *value, PyObject *tb) {
#if CYTHON_COMPILING_IN_CPYTHON
PyObject *tmp_type, *tmp_value, *tmp_tb;
PyThreadState *tstate = PyThreadState_GET();
tmp_type = tstate->curexc_type;
tmp_value = tstate->curexc_value;
tmp_tb = tstate->curexc_traceback;
tstate->curexc_type = type;
tstate->curexc_value = value;
tstate->curexc_traceback = tb;
Py_XDECREF(tmp_type);
Py_XDECREF(tmp_value);
Py_XDECREF(tmp_tb);
#else
PyErr_Restore(type, value, tb);
#endif
}
static CYTHON_INLINE void __Pyx_ErrFetch(PyObject **type, PyObject **value, PyObject **tb) {
#if CYTHON_COMPILING_IN_CPYTHON
PyThreadState *tstate = PyThreadState_GET();
*type = tstate->curexc_type;
*value = tstate->curexc_value;
*tb = tstate->curexc_traceback;
tstate->curexc_type = 0;
tstate->curexc_value = 0;
tstate->curexc_traceback = 0;
#else
PyErr_Fetch(type, value, tb);
#endif
}
#if PY_MAJOR_VERSION < 3
static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb,
CYTHON_UNUSED PyObject *cause) {
Py_XINCREF(type);
if (!value || value == Py_None)
value = NULL;
else
Py_INCREF(value);
if (!tb || tb == Py_None)
tb = NULL;
else {
Py_INCREF(tb);
if (!PyTraceBack_Check(tb)) {
PyErr_SetString(PyExc_TypeError,
"raise: arg 3 must be a traceback or None");
goto raise_error;
}
}
#if PY_VERSION_HEX < 0x02050000
if (PyClass_Check(type)) {
#else
if (PyType_Check(type)) {
#endif
#if CYTHON_COMPILING_IN_PYPY
if (!value) {
Py_INCREF(Py_None);
value = Py_None;
}
#endif
PyErr_NormalizeException(&type, &value, &tb);
} else {
if (value) {
PyErr_SetString(PyExc_TypeError,
"instance exception may not have a separate value");
goto raise_error;
}
value = type;
#if PY_VERSION_HEX < 0x02050000
if (PyInstance_Check(type)) {
type = (PyObject*) ((PyInstanceObject*)type)->in_class;
Py_INCREF(type);
} else {
type = 0;
PyErr_SetString(PyExc_TypeError,
"raise: exception must be an old-style class or instance");
goto raise_error;
}
#else
type = (PyObject*) Py_TYPE(type);
Py_INCREF(type);
if (!PyType_IsSubtype((PyTypeObject *)type, (PyTypeObject *)PyExc_BaseException)) {
PyErr_SetString(PyExc_TypeError,
"raise: exception class must be a subclass of BaseException");
goto raise_error;
}
#endif
}
__Pyx_ErrRestore(type, value, tb);
return;
raise_error:
Py_XDECREF(value);
Py_XDECREF(type);
Py_XDECREF(tb);
return;
}
#else /* Python 3+ */
static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause) {
PyObject* owned_instance = NULL;
if (tb == Py_None) {
tb = 0;
} else if (tb && !PyTraceBack_Check(tb)) {
PyErr_SetString(PyExc_TypeError,
"raise: arg 3 must be a traceback or None");
goto bad;
}
if (value == Py_None)
value = 0;
if (PyExceptionInstance_Check(type)) {
if (value) {
PyErr_SetString(PyExc_TypeError,
"instance exception may not have a separate value");
goto bad;
}
value = type;
type = (PyObject*) Py_TYPE(value);
} else if (PyExceptionClass_Check(type)) {
PyObject *instance_class = NULL;
if (value && PyExceptionInstance_Check(value)) {
instance_class = (PyObject*) Py_TYPE(value);
if (instance_class != type) {
if (PyObject_IsSubclass(instance_class, type)) {
type = instance_class;
} else {
instance_class = NULL;
}
}
}
if (!instance_class) {
PyObject *args;
if (!value)
args = PyTuple_New(0);
else if (PyTuple_Check(value)) {
Py_INCREF(value);
args = value;
} else
args = PyTuple_Pack(1, value);
if (!args)
goto bad;
owned_instance = PyObject_Call(type, args, NULL);
Py_DECREF(args);
if (!owned_instance)
goto bad;
value = owned_instance;
if (!PyExceptionInstance_Check(value)) {
PyErr_Format(PyExc_TypeError,
"calling %R should have returned an instance of "
"BaseException, not %R",
type, Py_TYPE(value));
goto bad;
}
}
} else {
PyErr_SetString(PyExc_TypeError,
"raise: exception class must be a subclass of BaseException");
goto bad;
}
#if PY_VERSION_HEX >= 0x03030000
if (cause) {
#else
if (cause && cause != Py_None) {
#endif
PyObject *fixed_cause;
if (cause == Py_None) {
fixed_cause = NULL;
} else if (PyExceptionClass_Check(cause)) {
fixed_cause = PyObject_CallObject(cause, NULL);
if (fixed_cause == NULL)
goto bad;
} else if (PyExceptionInstance_Check(cause)) {
fixed_cause = cause;
Py_INCREF(fixed_cause);
} else {
PyErr_SetString(PyExc_TypeError,
"exception causes must derive from "
"BaseException");
goto bad;
}
PyException_SetCause(value, fixed_cause);
}
PyErr_SetObject(type, value);
if (tb) {
PyThreadState *tstate = PyThreadState_GET();
PyObject* tmp_tb = tstate->curexc_traceback;
if (tb != tmp_tb) {
Py_INCREF(tb);
tstate->curexc_traceback = tb;
Py_XDECREF(tmp_tb);
}
}
bad:
Py_XDECREF(owned_instance);
return;
}
#endif
static CYTHON_INLINE Py_UCS4 __Pyx_GetItemInt_Unicode_Fast(PyObject* ustring, Py_ssize_t i,
int wraparound, int boundscheck) {
Py_ssize_t length;
#if CYTHON_PEP393_ENABLED
if (unlikely(__Pyx_PyUnicode_READY(ustring) < 0)) return (Py_UCS4)-1;
#endif
if (wraparound | boundscheck) {
length = __Pyx_PyUnicode_GET_LENGTH(ustring);
if (wraparound & unlikely(i < 0)) i += length;
if ((!boundscheck) || likely((0 <= i) & (i < length))) {
return __Pyx_PyUnicode_READ_CHAR(ustring, i);
} else {
PyErr_SetString(PyExc_IndexError, "string index out of range");
return (Py_UCS4)-1;
}
} else {
return __Pyx_PyUnicode_READ_CHAR(ustring, i);
}
}
static CYTHON_INLINE PyObject* __Pyx_PyUnicode_Substring(
PyObject* text, Py_ssize_t start, Py_ssize_t stop) {
Py_ssize_t length;
#if CYTHON_PEP393_ENABLED
if (unlikely(PyUnicode_READY(text) == -1)) return NULL;
length = PyUnicode_GET_LENGTH(text);
#else
length = PyUnicode_GET_SIZE(text);
#endif
if (start < 0) {
start += length;
if (start < 0)
start = 0;
}
if (stop < 0)
stop += length;
else if (stop > length)
stop = length;
length = stop - start;
if (length <= 0)
return PyUnicode_FromUnicode(NULL, 0);
#if CYTHON_PEP393_ENABLED
return PyUnicode_FromKindAndData(PyUnicode_KIND(text),
PyUnicode_1BYTE_DATA(text) + start*PyUnicode_KIND(text), stop-start);
#else
return PyUnicode_FromUnicode(PyUnicode_AS_UNICODE(text)+start, stop-start);
#endif
}
static CYTHON_INLINE int __Pyx_SetItemInt_Generic(PyObject *o, PyObject *j, PyObject *v) {
int r;
if (!j) return -1;
r = PyObject_SetItem(o, j, v);
Py_DECREF(j);
return r;
}
static CYTHON_INLINE int __Pyx_SetItemInt_Fast(PyObject *o, Py_ssize_t i, PyObject *v,
int is_list, int wraparound, int boundscheck) {
#if CYTHON_COMPILING_IN_CPYTHON
if (is_list || PyList_CheckExact(o)) {
Py_ssize_t n = (!wraparound) ? i : ((likely(i >= 0)) ? i : i + PyList_GET_SIZE(o));
if ((!boundscheck) || likely((n >= 0) & (n < PyList_GET_SIZE(o)))) {
PyObject* old = PyList_GET_ITEM(o, n);
Py_INCREF(v);
PyList_SET_ITEM(o, n, v);
Py_DECREF(old);
return 1;
}
} else {
PySequenceMethods *m = Py_TYPE(o)->tp_as_sequence;
if (likely(m && m->sq_ass_item)) {
if (wraparound && unlikely(i < 0) && likely(m->sq_length)) {
Py_ssize_t l = m->sq_length(o);
if (likely(l >= 0)) {
i += l;
} else {
if (PyErr_ExceptionMatches(PyExc_OverflowError))
PyErr_Clear();
else
return -1;
}
}
return m->sq_ass_item(o, i, v);
}
}
#else
#if CYTHON_COMPILING_IN_PYPY
if (is_list || (PySequence_Check(o) && !PyDict_Check(o))) {
#else
if (is_list || PySequence_Check(o)) {
#endif
return PySequence_SetItem(o, i, v);
}
#endif
return __Pyx_SetItemInt_Generic(o, PyInt_FromSsize_t(i), v);
}
static void __Pyx_WriteUnraisable(const char *name, CYTHON_UNUSED int clineno,
CYTHON_UNUSED int lineno, CYTHON_UNUSED const char *filename,
int full_traceback) {
PyObject *old_exc, *old_val, *old_tb;
PyObject *ctx;
__Pyx_ErrFetch(&old_exc, &old_val, &old_tb);
if (full_traceback) {
Py_XINCREF(old_exc);
Py_XINCREF(old_val);
Py_XINCREF(old_tb);
__Pyx_ErrRestore(old_exc, old_val, old_tb);
PyErr_PrintEx(1);
}
#if PY_MAJOR_VERSION < 3
ctx = PyString_FromString(name);
#else
ctx = PyUnicode_FromString(name);
#endif
__Pyx_ErrRestore(old_exc, old_val, old_tb);
if (!ctx) {
PyErr_WriteUnraisable(Py_None);
} else {
PyErr_WriteUnraisable(ctx);
Py_DECREF(ctx);
}
}
* Reading in tokenization rules correctly. Passing tests.
2014-07-07 02:02:55 +04:00
static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) {
PyObject* value = __Pyx_PyObject_GetAttrStr(module, name);
if (unlikely(!value) && PyErr_ExceptionMatches(PyExc_AttributeError)) {
PyErr_Format(PyExc_ImportError,
#if PY_MAJOR_VERSION < 3
"cannot import name %.230s", PyString_AS_STRING(name));
#else
"cannot import name %S", name);
#endif
}
return value;
}
static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) {
PyObject *empty_list = 0;
PyObject *module = 0;
PyObject *global_dict = 0;
PyObject *empty_dict = 0;
PyObject *list;
#if PY_VERSION_HEX < 0x03030000
PyObject *py_import;
py_import = __Pyx_PyObject_GetAttrStr(__pyx_b, __pyx_n_s_import);
if (!py_import)
goto bad;
#endif
if (from_list)
list = from_list;
else {
empty_list = PyList_New(0);
if (!empty_list)
goto bad;
list = empty_list;
}
global_dict = PyModule_GetDict(__pyx_m);
if (!global_dict)
goto bad;
empty_dict = PyDict_New();
if (!empty_dict)
goto bad;
#if PY_VERSION_HEX >= 0x02050000
{
#if PY_MAJOR_VERSION >= 3
if (level == -1) {
if (strchr(__Pyx_MODULE_NAME, '.')) {
#if PY_VERSION_HEX < 0x03030000
PyObject *py_level = PyInt_FromLong(1);
if (!py_level)
goto bad;
module = PyObject_CallFunctionObjArgs(py_import,
name, global_dict, empty_dict, list, py_level, NULL);
Py_DECREF(py_level);
#else
module = PyImport_ImportModuleLevelObject(
name, global_dict, empty_dict, list, 1);
#endif
if (!module) {
if (!PyErr_ExceptionMatches(PyExc_ImportError))
goto bad;
PyErr_Clear();
}
}
level = 0; /* try absolute import on failure */
}
#endif
if (!module) {
#if PY_VERSION_HEX < 0x03030000
PyObject *py_level = PyInt_FromLong(level);
if (!py_level)
goto bad;
module = PyObject_CallFunctionObjArgs(py_import,
name, global_dict, empty_dict, list, py_level, NULL);
Py_DECREF(py_level);
#else
module = PyImport_ImportModuleLevelObject(
name, global_dict, empty_dict, list, level);
#endif
}
}
#else
if (level>0) {
PyErr_SetString(PyExc_RuntimeError, "Relative import is not supported for Python <=2.4.");
goto bad;
}
module = PyObject_CallFunctionObjArgs(py_import,
name, global_dict, empty_dict, list, NULL);
#endif
bad:
#if PY_VERSION_HEX < 0x03030000
Py_XDECREF(py_import);
#endif
Py_XDECREF(empty_list);
Py_XDECREF(empty_dict);
return module;
}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
#define __PYX_VERIFY_RETURN_INT(target_type, func_type, func) \
{ \
func_type value = func(x); \
if (sizeof(target_type) < sizeof(func_type)) { \
if (unlikely(value != (func_type) (target_type) value)) { \
func_type zero = 0; \
PyErr_SetString(PyExc_OverflowError, \
(is_unsigned && unlikely(value < zero)) ? \
"can't convert negative value to " #target_type : \
"value too large to convert to " #target_type); \
return (target_type) -1; \
} \
} \
return (target_type) value; \
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) {
const int neg_one = (int) -1, const_zero = 0;
const int is_unsigned = neg_one > const_zero;
#if PY_MAJOR_VERSION < 3
if (likely(PyInt_Check(x))) {
if (sizeof(int) < sizeof(long)) {
__PYX_VERIFY_RETURN_INT(int, long, PyInt_AS_LONG)
} else {
long val = PyInt_AS_LONG(x);
if (is_unsigned && unlikely(val < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to int");
return (int) -1;
}
return (int) val;
}
} else
#endif
if (likely(PyLong_Check(x))) {
if (is_unsigned) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(int)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return (int) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (unlikely(Py_SIZE(x) < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to int");
return (int) -1;
}
if (sizeof(int) <= sizeof(unsigned long)) {
__PYX_VERIFY_RETURN_INT(int, unsigned long, PyLong_AsUnsignedLong)
} else if (sizeof(int) <= sizeof(unsigned long long)) {
__PYX_VERIFY_RETURN_INT(int, unsigned long long, PyLong_AsUnsignedLongLong)
}
} else {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(int)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return +(int) ((PyLongObject*)x)->ob_digit[0];
case -1: return -(int) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (sizeof(int) <= sizeof(long)) {
__PYX_VERIFY_RETURN_INT(int, long, PyLong_AsLong)
} else if (sizeof(int) <= sizeof(long long)) {
__PYX_VERIFY_RETURN_INT(int, long long, PyLong_AsLongLong)
}
}
{
#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
PyErr_SetString(PyExc_RuntimeError,
"_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
#else
int val;
PyObject *v = __Pyx_PyNumber_Int(x);
#if PY_MAJOR_VERSION < 3
if (likely(v) && !PyLong_Check(v)) {
PyObject *tmp = v;
v = PyNumber_Long(tmp);
Py_DECREF(tmp);
}
#endif
if (likely(v)) {
int one = 1; int is_little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&val;
int ret = _PyLong_AsByteArray((PyLongObject *)v,
bytes, sizeof(val),
is_little, !is_unsigned);
Py_DECREF(v);
if (likely(!ret))
return val;
}
#endif
return (int) -1;
}
} else {
int val;
PyObject *tmp = __Pyx_PyNumber_Int(x);
if (!tmp) return (int) -1;
val = __Pyx_PyInt_As_int(tmp);
Py_DECREF(tmp);
return val;
}
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
static CYTHON_INLINE uint64_t __Pyx_PyInt_As_uint64_t(PyObject *x) {
const uint64_t neg_one = (uint64_t) -1, const_zero = 0;
const int is_unsigned = neg_one > const_zero;
#if PY_MAJOR_VERSION < 3
if (likely(PyInt_Check(x))) {
if (sizeof(uint64_t) < sizeof(long)) {
__PYX_VERIFY_RETURN_INT(uint64_t, long, PyInt_AS_LONG)
} else {
long val = PyInt_AS_LONG(x);
if (is_unsigned && unlikely(val < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to uint64_t");
return (uint64_t) -1;
}
return (uint64_t) val;
}
} else
#endif
if (likely(PyLong_Check(x))) {
if (is_unsigned) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(uint64_t)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return (uint64_t) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (unlikely(Py_SIZE(x) < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to uint64_t");
return (uint64_t) -1;
}
if (sizeof(uint64_t) <= sizeof(unsigned long)) {
__PYX_VERIFY_RETURN_INT(uint64_t, unsigned long, PyLong_AsUnsignedLong)
} else if (sizeof(uint64_t) <= sizeof(unsigned long long)) {
__PYX_VERIFY_RETURN_INT(uint64_t, unsigned long long, PyLong_AsUnsignedLongLong)
}
} else {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(uint64_t)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return +(uint64_t) ((PyLongObject*)x)->ob_digit[0];
case -1: return -(uint64_t) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (sizeof(uint64_t) <= sizeof(long)) {
__PYX_VERIFY_RETURN_INT(uint64_t, long, PyLong_AsLong)
} else if (sizeof(uint64_t) <= sizeof(long long)) {
__PYX_VERIFY_RETURN_INT(uint64_t, long long, PyLong_AsLongLong)
}
}
{
#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
PyErr_SetString(PyExc_RuntimeError,
"_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
#else
uint64_t val;
PyObject *v = __Pyx_PyNumber_Int(x);
#if PY_MAJOR_VERSION < 3
if (likely(v) && !PyLong_Check(v)) {
PyObject *tmp = v;
v = PyNumber_Long(tmp);
Py_DECREF(tmp);
}
#endif
if (likely(v)) {
int one = 1; int is_little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&val;
int ret = _PyLong_AsByteArray((PyLongObject *)v,
bytes, sizeof(val),
is_little, !is_unsigned);
Py_DECREF(v);
if (likely(!ret))
return val;
}
#endif
return (uint64_t) -1;
}
} else {
uint64_t val;
PyObject *tmp = __Pyx_PyNumber_Int(x);
if (!tmp) return (uint64_t) -1;
val = __Pyx_PyInt_As_uint64_t(tmp);
Py_DECREF(tmp);
return val;
}
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
static CYTHON_INLINE size_t __Pyx_PyInt_As_size_t(PyObject *x) {
const size_t neg_one = (size_t) -1, const_zero = 0;
const int is_unsigned = neg_one > const_zero;
#if PY_MAJOR_VERSION < 3
if (likely(PyInt_Check(x))) {
if (sizeof(size_t) < sizeof(long)) {
__PYX_VERIFY_RETURN_INT(size_t, long, PyInt_AS_LONG)
} else {
long val = PyInt_AS_LONG(x);
if (is_unsigned && unlikely(val < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to size_t");
return (size_t) -1;
}
return (size_t) val;
}
} else
#endif
if (likely(PyLong_Check(x))) {
if (is_unsigned) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(size_t)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return (size_t) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (unlikely(Py_SIZE(x) < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to size_t");
return (size_t) -1;
}
if (sizeof(size_t) <= sizeof(unsigned long)) {
__PYX_VERIFY_RETURN_INT(size_t, unsigned long, PyLong_AsUnsignedLong)
} else if (sizeof(size_t) <= sizeof(unsigned long long)) {
__PYX_VERIFY_RETURN_INT(size_t, unsigned long long, PyLong_AsUnsignedLongLong)
}
} else {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(size_t)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return +(size_t) ((PyLongObject*)x)->ob_digit[0];
case -1: return -(size_t) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (sizeof(size_t) <= sizeof(long)) {
__PYX_VERIFY_RETURN_INT(size_t, long, PyLong_AsLong)
} else if (sizeof(size_t) <= sizeof(long long)) {
__PYX_VERIFY_RETURN_INT(size_t, long long, PyLong_AsLongLong)
}
}
{
#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
PyErr_SetString(PyExc_RuntimeError,
"_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
#else
size_t val;
PyObject *v = __Pyx_PyNumber_Int(x);
#if PY_MAJOR_VERSION < 3
if (likely(v) && !PyLong_Check(v)) {
PyObject *tmp = v;
v = PyNumber_Long(tmp);
Py_DECREF(tmp);
}
#endif
if (likely(v)) {
int one = 1; int is_little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&val;
int ret = _PyLong_AsByteArray((PyLongObject *)v,
bytes, sizeof(val),
is_little, !is_unsigned);
Py_DECREF(v);
if (likely(!ret))
return val;
}
#endif
return (size_t) -1;
}
} else {
size_t val;
PyObject *tmp = __Pyx_PyNumber_Int(x);
if (!tmp) return (size_t) -1;
val = __Pyx_PyInt_As_size_t(tmp);
Py_DECREF(tmp);
return val;
}
}
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_uint64_t(uint64_t value) {
const uint64_t neg_one = (uint64_t) -1, const_zero = 0;
const int is_unsigned = neg_one > const_zero;
if (is_unsigned) {
if (sizeof(uint64_t) < sizeof(long)) {
return PyInt_FromLong((long) value);
} else if (sizeof(uint64_t) <= sizeof(unsigned long)) {
return PyLong_FromUnsignedLong((unsigned long) value);
} else if (sizeof(uint64_t) <= sizeof(unsigned long long)) {
return PyLong_FromUnsignedLongLong((unsigned long long) value);
}
} else {
if (sizeof(uint64_t) <= sizeof(long)) {
return PyInt_FromLong((long) value);
} else if (sizeof(uint64_t) <= sizeof(long long)) {
return PyLong_FromLongLong((long long) value);
}
}
{
int one = 1; int little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&value;
return _PyLong_FromByteArray(bytes, sizeof(uint64_t),
little, !is_unsigned);
}
}
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) {
const long neg_one = (long) -1, const_zero = 0;
const int is_unsigned = neg_one > const_zero;
if (is_unsigned) {
if (sizeof(long) < sizeof(long)) {
return PyInt_FromLong((long) value);
} else if (sizeof(long) <= sizeof(unsigned long)) {
return PyLong_FromUnsignedLong((unsigned long) value);
} else if (sizeof(long) <= sizeof(unsigned long long)) {
return PyLong_FromUnsignedLongLong((unsigned long long) value);
}
} else {
if (sizeof(long) <= sizeof(long)) {
return PyInt_FromLong((long) value);
} else if (sizeof(long) <= sizeof(long long)) {
return PyLong_FromLongLong((long long) value);
}
}
{
int one = 1; int little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&value;
return _PyLong_FromByteArray(bytes, sizeof(long),
little, !is_unsigned);
}
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) {
const long neg_one = (long) -1, const_zero = 0;
const int is_unsigned = neg_one > const_zero;
#if PY_MAJOR_VERSION < 3
if (likely(PyInt_Check(x))) {
if (sizeof(long) < sizeof(long)) {
__PYX_VERIFY_RETURN_INT(long, long, PyInt_AS_LONG)
} else {
long val = PyInt_AS_LONG(x);
if (is_unsigned && unlikely(val < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to long");
return (long) -1;
}
return (long) val;
}
} else
#endif
if (likely(PyLong_Check(x))) {
if (is_unsigned) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(long)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return (long) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (unlikely(Py_SIZE(x) < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to long");
return (long) -1;
}
if (sizeof(long) <= sizeof(unsigned long)) {
__PYX_VERIFY_RETURN_INT(long, unsigned long, PyLong_AsUnsignedLong)
} else if (sizeof(long) <= sizeof(unsigned long long)) {
__PYX_VERIFY_RETURN_INT(long, unsigned long long, PyLong_AsUnsignedLongLong)
}
} else {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(long)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return +(long) ((PyLongObject*)x)->ob_digit[0];
case -1: return -(long) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (sizeof(long) <= sizeof(long)) {
__PYX_VERIFY_RETURN_INT(long, long, PyLong_AsLong)
} else if (sizeof(long) <= sizeof(long long)) {
__PYX_VERIFY_RETURN_INT(long, long long, PyLong_AsLongLong)
}
}
{
#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
PyErr_SetString(PyExc_RuntimeError,
"_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
#else
long val;
PyObject *v = __Pyx_PyNumber_Int(x);
#if PY_MAJOR_VERSION < 3
if (likely(v) && !PyLong_Check(v)) {
PyObject *tmp = v;
v = PyNumber_Long(tmp);
Py_DECREF(tmp);
}
#endif
if (likely(v)) {
int one = 1; int is_little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&val;
int ret = _PyLong_AsByteArray((PyLongObject *)v,
bytes, sizeof(val),
is_little, !is_unsigned);
Py_DECREF(v);
if (likely(!ret))
return val;
}
#endif
return (long) -1;
}
} else {
long val;
PyObject *tmp = __Pyx_PyNumber_Int(x);
if (!tmp) return (long) -1;
val = __Pyx_PyInt_As_long(tmp);
Py_DECREF(tmp);
return val;
}
}
static int __Pyx_check_binary_version(void) {
char ctversion[4], rtversion[4];
PyOS_snprintf(ctversion, 4, "%d.%d", PY_MAJOR_VERSION, PY_MINOR_VERSION);
PyOS_snprintf(rtversion, 4, "%s", Py_GetVersion());
if (ctversion[0] != rtversion[0] || ctversion[2] != rtversion[2]) {
char message[200];
PyOS_snprintf(message, sizeof(message),
"compiletime version %s of module '%.100s' "
"does not match runtime version %s",
ctversion, __Pyx_MODULE_NAME, rtversion);
#if PY_VERSION_HEX < 0x02050000
return PyErr_Warn(NULL, message);
#else
return PyErr_WarnEx(NULL, message, 1);
#endif
}
return 0;
}
static int __Pyx_ExportVoidPtr(PyObject *name, void *p, const char *sig) {
PyObject *d;
PyObject *cobj = 0;
d = PyDict_GetItem(__pyx_d, __pyx_n_s_pyx_capi);
Py_XINCREF(d);
if (!d) {
d = PyDict_New();
if (!d)
goto bad;
if (__Pyx_PyObject_SetAttrStr(__pyx_m, __pyx_n_s_pyx_capi, d) < 0)
goto bad;
}
#if PY_VERSION_HEX >= 0x02070000 && !(PY_MAJOR_VERSION==3 && PY_MINOR_VERSION==0)
cobj = PyCapsule_New(p, sig, 0);
#else
cobj = PyCObject_FromVoidPtrAndDesc(p, (void *)sig, 0);
#endif
if (!cobj)
goto bad;
if (PyDict_SetItem(d, name, cobj) < 0)
goto bad;
Py_DECREF(cobj);
Py_DECREF(d);
return 0;
bad:
Py_XDECREF(cobj);
Py_XDECREF(d);
return -1;
}
static int __Pyx_ExportFunction(const char *name, void (*f)(void), const char *sig) {
PyObject *d = 0;
PyObject *cobj = 0;
union {
void (*fp)(void);
void *p;
} tmp;
d = PyObject_GetAttrString(__pyx_m, (char *)"__pyx_capi__");
if (!d) {
PyErr_Clear();
d = PyDict_New();
if (!d)
goto bad;
Py_INCREF(d);
if (PyModule_AddObject(__pyx_m, (char *)"__pyx_capi__", d) < 0)
goto bad;
}
tmp.fp = f;
#if PY_VERSION_HEX >= 0x02070000 && !(PY_MAJOR_VERSION==3&&PY_MINOR_VERSION==0)
cobj = PyCapsule_New(tmp.p, sig, 0);
#else
cobj = PyCObject_FromVoidPtrAndDesc(tmp.p, (void *)sig, 0);
#endif
if (!cobj)
goto bad;
if (PyDict_SetItemString(d, name, cobj) < 0)
goto bad;
Py_DECREF(cobj);
Py_DECREF(d);
return 0;
bad:
Py_XDECREF(cobj);
Py_XDECREF(d);
return -1;
}
static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) {
int start = 0, mid = 0, end = count - 1;
if (end >= 0 && code_line > entries[end].code_line) {
return count;
}
while (start < end) {
mid = (start + end) / 2;
if (code_line < entries[mid].code_line) {
end = mid;
} else if (code_line > entries[mid].code_line) {
start = mid + 1;
} else {
return mid;
}
}
if (code_line <= entries[mid].code_line) {
return mid;
} else {
return mid + 1;
}
}
static PyCodeObject *__pyx_find_code_object(int code_line) {
PyCodeObject* code_object;
int pos;
if (unlikely(!code_line) || unlikely(!__pyx_code_cache.entries)) {
return NULL;
}
pos = __pyx_bisect_code_objects(__pyx_code_cache.entries, __pyx_code_cache.count, code_line);
if (unlikely(pos >= __pyx_code_cache.count) || unlikely(__pyx_code_cache.entries[pos].code_line != code_line)) {
return NULL;
}
code_object = __pyx_code_cache.entries[pos].code_object;
Py_INCREF(code_object);
return code_object;
}
static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) {
int pos, i;
__Pyx_CodeObjectCacheEntry* entries = __pyx_code_cache.entries;
if (unlikely(!code_line)) {
return;
}
if (unlikely(!entries)) {
entries = (__Pyx_CodeObjectCacheEntry*)PyMem_Malloc(64*sizeof(__Pyx_CodeObjectCacheEntry));
if (likely(entries)) {
__pyx_code_cache.entries = entries;
__pyx_code_cache.max_count = 64;
__pyx_code_cache.count = 1;
entries[0].code_line = code_line;
entries[0].code_object = code_object;
Py_INCREF(code_object);
}
return;
}
pos = __pyx_bisect_code_objects(__pyx_code_cache.entries, __pyx_code_cache.count, code_line);
if ((pos < __pyx_code_cache.count) && unlikely(__pyx_code_cache.entries[pos].code_line == code_line)) {
PyCodeObject* tmp = entries[pos].code_object;
entries[pos].code_object = code_object;
Py_DECREF(tmp);
return;
}
if (__pyx_code_cache.count == __pyx_code_cache.max_count) {
int new_max = __pyx_code_cache.max_count + 64;
entries = (__Pyx_CodeObjectCacheEntry*)PyMem_Realloc(
__pyx_code_cache.entries, new_max*sizeof(__Pyx_CodeObjectCacheEntry));
if (unlikely(!entries)) {
return;
}
__pyx_code_cache.entries = entries;
__pyx_code_cache.max_count = new_max;
}
for (i=__pyx_code_cache.count; i>pos; i--) {
entries[i] = entries[i-1];
}
entries[pos].code_line = code_line;
entries[pos].code_object = code_object;
__pyx_code_cache.count++;
Py_INCREF(code_object);
}
#include "compile.h"
#include "frameobject.h"
#include "traceback.h"
static PyCodeObject* __Pyx_CreateCodeObjectForTraceback(
const char *funcname, int c_line,
int py_line, const char *filename) {
PyCodeObject *py_code = 0;
PyObject *py_srcfile = 0;
PyObject *py_funcname = 0;
#if PY_MAJOR_VERSION < 3
py_srcfile = PyString_FromString(filename);
#else
py_srcfile = PyUnicode_FromString(filename);
#endif
if (!py_srcfile) goto bad;
if (c_line) {
#if PY_MAJOR_VERSION < 3
py_funcname = PyString_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line);
#else
py_funcname = PyUnicode_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line);
#endif
}
else {
#if PY_MAJOR_VERSION < 3
py_funcname = PyString_FromString(funcname);
#else
py_funcname = PyUnicode_FromString(funcname);
#endif
}
if (!py_funcname) goto bad;
py_code = __Pyx_PyCode_New(
0, /*int argcount,*/
0, /*int kwonlyargcount,*/
0, /*int nlocals,*/
0, /*int stacksize,*/
0, /*int flags,*/
__pyx_empty_bytes, /*PyObject *code,*/
__pyx_empty_tuple, /*PyObject *consts,*/
__pyx_empty_tuple, /*PyObject *names,*/
__pyx_empty_tuple, /*PyObject *varnames,*/
__pyx_empty_tuple, /*PyObject *freevars,*/
__pyx_empty_tuple, /*PyObject *cellvars,*/
py_srcfile, /*PyObject *filename,*/
py_funcname, /*PyObject *name,*/
py_line, /*int firstlineno,*/
__pyx_empty_bytes /*PyObject *lnotab*/
);
Py_DECREF(py_srcfile);
Py_DECREF(py_funcname);
return py_code;
bad:
Py_XDECREF(py_srcfile);
Py_XDECREF(py_funcname);
return NULL;
}
static void __Pyx_AddTraceback(const char *funcname, int c_line,
int py_line, const char *filename) {
PyCodeObject *py_code = 0;
PyObject *py_globals = 0;
PyFrameObject *py_frame = 0;
py_code = __pyx_find_code_object(c_line ? c_line : py_line);
if (!py_code) {
py_code = __Pyx_CreateCodeObjectForTraceback(
funcname, c_line, py_line, filename);
if (!py_code) goto bad;
__pyx_insert_code_object(c_line ? c_line : py_line, py_code);
}
py_globals = PyModule_GetDict(__pyx_m);
if (!py_globals) goto bad;
py_frame = PyFrame_New(
PyThreadState_GET(), /*PyThreadState *tstate,*/
py_code, /*PyCodeObject *code,*/
py_globals, /*PyObject *globals,*/
0 /*PyObject *locals*/
);
if (!py_frame) goto bad;
py_frame->f_lineno = py_line;
PyTraceBack_Here(py_frame);
bad:
Py_XDECREF(py_code);
Py_XDECREF(py_frame);
}
static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) {
while (t->p) {
#if PY_MAJOR_VERSION < 3
if (t->is_unicode) {
*t->p = PyUnicode_DecodeUTF8(t->s, t->n - 1, NULL);
} else if (t->intern) {
*t->p = PyString_InternFromString(t->s);
} else {
*t->p = PyString_FromStringAndSize(t->s, t->n - 1);
}
#else /* Python 3+ has unicode identifiers */
if (t->is_unicode | t->is_str) {
if (t->intern) {
*t->p = PyUnicode_InternFromString(t->s);
} else if (t->encoding) {
*t->p = PyUnicode_Decode(t->s, t->n - 1, t->encoding, NULL);
} else {
*t->p = PyUnicode_FromStringAndSize(t->s, t->n - 1);
}
} else {
*t->p = PyBytes_FromStringAndSize(t->s, t->n - 1);
}
#endif
if (!*t->p)
return -1;
++t;
}
return 0;
}
static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(char* c_str) {
return __Pyx_PyUnicode_FromStringAndSize(c_str, strlen(c_str));
}
static CYTHON_INLINE char* __Pyx_PyObject_AsString(PyObject* o) {
Py_ssize_t ignore;
return __Pyx_PyObject_AsStringAndSize(o, &ignore);
}
static CYTHON_INLINE char* __Pyx_PyObject_AsStringAndSize(PyObject* o, Py_ssize_t *length) {
#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT
if (
#if PY_MAJOR_VERSION < 3 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
__Pyx_sys_getdefaultencoding_not_ascii &&
#endif
PyUnicode_Check(o)) {
#if PY_VERSION_HEX < 0x03030000
char* defenc_c;
PyObject* defenc = _PyUnicode_AsDefaultEncodedString(o, NULL);
if (!defenc) return NULL;
defenc_c = PyBytes_AS_STRING(defenc);
#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
{
char* end = defenc_c + PyBytes_GET_SIZE(defenc);
char* c;
for (c = defenc_c; c < end; c++) {
if ((unsigned char) (*c) >= 128) {
PyUnicode_AsASCIIString(o);
return NULL;
}
}
}
#endif /*__PYX_DEFAULT_STRING_ENCODING_IS_ASCII*/
*length = PyBytes_GET_SIZE(defenc);
return defenc_c;
#else /* PY_VERSION_HEX < 0x03030000 */
if (PyUnicode_READY(o) == -1) return NULL;
#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
if (PyUnicode_IS_ASCII(o)) {
*length = PyUnicode_GET_DATA_SIZE(o);
return PyUnicode_AsUTF8(o);
} else {
PyUnicode_AsASCIIString(o);
return NULL;
}
#else /* __PYX_DEFAULT_STRING_ENCODING_IS_ASCII */
return PyUnicode_AsUTF8AndSize(o, length);
#endif /* __PYX_DEFAULT_STRING_ENCODING_IS_ASCII */
#endif /* PY_VERSION_HEX < 0x03030000 */
} else
#endif /* __PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT */
#if !CYTHON_COMPILING_IN_PYPY
#if PY_VERSION_HEX >= 0x02060000
if (PyByteArray_Check(o)) {
*length = PyByteArray_GET_SIZE(o);
return PyByteArray_AS_STRING(o);
} else
#endif
#endif
{
char* result;
int r = PyBytes_AsStringAndSize(o, &result, length);
if (unlikely(r < 0)) {
return NULL;
} else {
return result;
}
}
}
static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject* x) {
int is_true = x == Py_True;
if (is_true | (x == Py_False) | (x == Py_None)) return is_true;
else return PyObject_IsTrue(x);
}
static CYTHON_INLINE PyObject* __Pyx_PyNumber_Int(PyObject* x) {
PyNumberMethods *m;
const char *name = NULL;
PyObject *res = NULL;
#if PY_MAJOR_VERSION < 3
if (PyInt_Check(x) || PyLong_Check(x))
#else
if (PyLong_Check(x))
#endif
return Py_INCREF(x), x;
m = Py_TYPE(x)->tp_as_number;
#if PY_MAJOR_VERSION < 3
if (m && m->nb_int) {
name = "int";
res = PyNumber_Int(x);
}
else if (m && m->nb_long) {
name = "long";
res = PyNumber_Long(x);
}
#else
if (m && m->nb_int) {
name = "int";
res = PyNumber_Long(x);
}
#endif
if (res) {
#if PY_MAJOR_VERSION < 3
if (!PyInt_Check(res) && !PyLong_Check(res)) {
#else
if (!PyLong_Check(res)) {
#endif
PyErr_Format(PyExc_TypeError,
"__%.4s__ returned non-%.4s (type %.200s)",
name, name, Py_TYPE(res)->tp_name);
Py_DECREF(res);
return NULL;
}
}
else if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_TypeError,
"an integer is required");
}
return res;
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) {
Py_ssize_t ival;
PyObject *x;
#if PY_MAJOR_VERSION < 3
if (likely(PyInt_CheckExact(b)))
return PyInt_AS_LONG(b);
#endif
if (likely(PyLong_CheckExact(b))) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
switch (Py_SIZE(b)) {
case -1: return -(sdigit)((PyLongObject*)b)->ob_digit[0];
case 0: return 0;
case 1: return ((PyLongObject*)b)->ob_digit[0];
}
#endif
#endif
#if PY_VERSION_HEX < 0x02060000
return PyInt_AsSsize_t(b);
#else
return PyLong_AsSsize_t(b);
#endif
}
x = PyNumber_Index(b);
if (!x) return -1;
ival = PyInt_AsSsize_t(x);
Py_DECREF(x);
return ival;
}
static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) {
#if PY_VERSION_HEX < 0x02050000
if (ival <= LONG_MAX)
return PyInt_FromLong((long)ival);
else {
unsigned char *bytes = (unsigned char *) &ival;
int one = 1; int little = (int)*(unsigned char*)&one;
return _PyLong_FromByteArray(bytes, sizeof(size_t), little, 0);
}
#else
return PyInt_FromSize_t(ival);
#endif
}
#endif /* Py_PYTHON_H */
Reference in New Issue Copy Permalink